SlideShare a Scribd company logo
1 of 15
Download to read offline
Transformational grammar
From Wikipedia, the free encyclopedia

In linguistics, a transformational grammar or transformational-generative grammar (TGG)
is a generative grammar, especially of a natural language, that has been developed in a
Chomskyan tradition. Additionally, transformational grammar is the Chomskyan tradition that
gives rise to specific transformational grammars. Much current research in transformational
grammar is inspired by Chomsky's Minimalist Program.[1]


Contents
[hide]

         1 Deep structure and surface structure
         2 Development of basic concepts
         3 Innate linguistic knowledge
         4 Grammatical theories
         5 "I-Language" and "E-Language"
         6 Grammaticality
         7 Minimalism
         8 Mathematical representation
         9 Transformations
         10 See also
         11 References
         12 External links



[edit] Deep structure and surface structure

                      Linguistics




                   Theoretical linguistics


                    Cognitive linguistics
Generative linguistics
Functional theories of grammar
    Quantitative linguistics
   Phonology · Graphemics
 Morphology · Syntax · Lexis
    Semantics · Pragmatics


   Descriptive linguistics


  Anthropological linguistics
   Comparative linguistics
     Historical linguistics
    Phonetics · Graphetics
 Etymology · Sociolinguistics


         Applied and
  experimental linguistics


  Computational linguistics
   Evolutionary linguistics
     Forensic linguistics
      Internet linguistics
    Language acquisition
    Language assessment
   Language development
     Language education
   Linguistic anthropology
       Neurolinguistics
      Psycholinguistics
 Second language acquisition


       Related articles


     History of linguistics
    Linguistic prescription
List of linguists

                List of unsolved problems
                       in linguistics


                         Portal


                                                v·d·e



In 1957, Noam Chomsky published Syntactic Structures, in which he developed the idea that
each sentence in a language has two levels of representation — a deep structure and a surface
structure.[2][3] The deep structure represented the core semantic relations of a sentence, and was
mapped on to the surface structure (which followed the phonological form of the sentence very
closely) via transformations. Chomsky believed there are considerable similarities between
languages' deep structures, and that these structures reveal properties, common to all languages
that surface structures conceal. However, this may not have been the central motivation for
introducing deep structure. Transformations had been proposed prior to the development of deep
structure as a means of increasing the mathematical and descriptive power of context-free
grammars. Similarly, deep structure was devised largely for technical reasons relating to early
semantic theory. Chomsky emphasizes the importance of modern formal mathematical devices in
the development of grammatical theory:

But the fundamental reason for [the] inadequacy of traditional grammars is a more technical one.
Although it was well understood that linguistic processes are in some sense "creative," the
technical devices for expressing a system of recursive processes were simply not available until
much more recently. In fact, a real understanding of how a language can (in Humboldt's words)
"make infinite use of finite means" has developed only within the last thirty years, in the course
of studies in the foundations of mathematics.
—Aspects of the Theory of Syntax

[edit] Development of basic concepts
Though transformations continue to be important in Chomsky's current theories, he has now
abandoned the original notion of Deep Structure and Surface Structure. Initially, two additional
levels of representation were introduced (LF — Logical Form, and PF — Phonetic Form), and
then in the 1990s Chomsky sketched out a new program of research known as Minimalism, in
which Deep Structure and Surface Structure no longer featured and PF and LF remained as the
only levels of representation.

To complicate the understanding of the development of Noam Chomsky's theories, the precise
meanings of Deep Structure and Surface Structure have changed over time — by the 1970s, the
two were normally referred to simply as D-Structure and S-Structure by Chomskyan linguists. In
particular, the idea that the meaning of a sentence was determined by its Deep Structure (taken to
its logical conclusions by the generative semanticists during the same period) was dropped for
good by Chomskyan linguists when LF took over this role (previously, Chomsky and Ray
Jackendoff had begun to argue that meaning was determined by both Deep and Surface
Structure).[4][5]

[edit] Innate linguistic knowledge
Terms such as "transformation" can give the impression that theories of transformational
generative grammar are intended as a model for the processes through which the human mind
constructs and understands sentences. Chomsky is clear that this is not in fact the case: a
generative grammar models only the knowledge that underlies the human ability to speak and
understand. One of the most important of Chomsky's ideas is that most of this knowledge is
innate, with the result that a baby can have a large body of prior knowledge about the structure of
language in general, and need only actually learn the idiosyncratic features of the language(s) it
is exposed to. Chomsky was not the first person to suggest that all languages had certain
fundamental things in common (he quotes philosophers writing several centuries ago who had
the same basic idea), but he helped to make the innateness theory respectable after a period
dominated by more behaviorist attitudes towards language. Perhaps more significantly, he made
concrete and technically sophisticated proposals about the structure of language, and made
important proposals regarding how the success of grammatical theories should be evaluated.

[edit] Grammatical theories
In the 1960s, Chomsky introduced two central ideas relevant to the construction and evaluation
of grammatical theories. The first was the distinction between competence and performance.
Chomsky noted the obvious fact that people, when speaking in the real world, often make
linguistic errors (e.g., starting a sentence and then abandoning it midway through). He argued
that these errors in linguistic performance were irrelevant to the study of linguistic competence
(the knowledge that allows people to construct and understand grammatical sentences).
Consequently, the linguist can study an idealised version of language, greatly simplifying
linguistic analysis (see the "Grammaticality" section below). The second idea related directly to
the evaluation of theories of grammar. Chomsky distinguished between grammars that achieve
descriptive adequacy and those that go further and achieved explanatory adequacy. A
descriptively adequate grammar for a particular language defines the (infinite) set of grammatical
sentences in that language; that is, it describes the language in its entirety. A grammar that
achieves explanatory adequacy has the additional property that it gives an insight into the
underlying linguistic structures in the human mind; that is, it does not merely describe the
grammar of a language, but makes predictions about how linguistic knowledge is mentally
represented. For Chomsky, the nature of such mental representations is largely innate, so if a
grammatical theory has explanatory adequacy it must be able to explain the various grammatical
nuances of the languages of the world as relatively minor variations in the universal pattern of
human language. Chomsky argued that, even though linguists were still a long way from
constructing descriptively adequate grammars, progress in terms of descriptive adequacy will
only come if linguists hold explanatory adequacy as their goal. In other words, real insight into
the structure of individual languages can only be gained through comparative study of a wide
range of languages, on the assumption that they are all cut from the same cloth.

[edit] "I-Language" and "E-Language"
In 1986, Chomsky proposed a distinction between I-Language and E-Language, similar but not
identical to the competence/performance distinction.[6] (I-language) refers to Internal language
and is contrasted with External Language (or E-language). I-Language is taken to be the object
of study in linguistic theory; it is the mentally represented linguistic knowledge that a native
speaker of a language has, and is therefore a mental object — from this perspective, most of
theoretical linguistics is a branch of psychology. E-Language encompasses all other notions of
what a language is, for example that it is a body of knowledge or behavioural habits shared by a
community. Thus, E-Language is not itself a coherent concept,[7] and Chomsky argues that such
notions of language are not useful in the study of innate linguistic knowledge, i.e., competence,
even though they may seem sensible and intuitive, and useful in other areas of study.
Competence, he argues, can only be studied if languages are treated as mental objects.

[edit] Grammaticality
Further information: Grammaticality

Chomsky argued that the notions "grammatical" and "ungrammatical" could be defined in a
meaningful and useful way. In contrast, an extreme behaviorist linguist would argue that
language can only be studied through recordings or transcriptions of actual speech, the role of the
linguist being to look for patterns in such observed speech, but not to hypothesize about why
such patterns might occur, nor to label particular utterances as either "grammatical" or
"ungrammatical." Although few linguists in the 1950s actually took such an extreme position,
Chomsky was at an opposite extreme, defining grammaticality in an unusually mentalistic way
(for the time).[8] He argued that the intuition of a native speaker is enough to define the
grammaticalness of a sentence; that is, if a particular string of English words elicits a double
take, or feeling of wrongness in a native English speaker, and when various extraneous factors
affecting intuitions are controlled for, it can be said that the string of words is ungrammatical.
This, according to Chomsky, is entirely distinct from the question of whether a sentence is
meaningful, or can be understood. It is possible for a sentence to be both grammatical and
meaningless, as in Chomsky's famous example "colorless green ideas sleep furiously." But such
sentences manifest a linguistic problem distinct from that posed by meaningful but
ungrammatical (non)-sentences such as "man the bit sandwich the," the meaning of which is
fairly clear, but no native speaker would accept as well formed.

The use of such intuitive judgments permitted generative syntacticians to base their research on a
methodology in which studying language through a corpus of observed speech became
downplayed, since the grammatical properties of constructed sentences were considered to be
appropriate data to build a grammatical model on.

[edit] Minimalism
Main article: Minimalist program

From the mid-1990s onwards, much research in transformational grammar has been inspired by
Chomsky's Minimalist Program.[9] The "Minimalist Program" aims at the further development of
ideas involving economy of derivation and economy of representation, which had started to
become significant in the early 1990s, but were still rather peripheral aspects of
Transformational-generative grammar theory.

       Economy of derivation is a principle stating that movements (i.e., transformations) only
       occur in order to match interpretable features with uninterpretable features. An example
       of an interpretable feature is the plural inflection on regular English nouns, e.g., dogs.
       The word dogs can only be used to refer to several dogs, not a single dog, and so this
       inflection contributes to meaning, making it interpretable. English verbs are inflected
       according to the number of their subject (e.g., "Dogs bite" vs "A dog bites"), but in most
       sentences this inflection just duplicates the information about number that the subject
       noun already has, and it is therefore uninterpretable.
       Economy of representation is the principle that grammatical structures must exist for a
       purpose, i.e., the structure of a sentence should be no larger or more complex than
       required to satisfy constraints on grammaticality.

Both notions, as described here, are somewhat vague, and indeed the precise formulation of these
principles is controversial.[10][11] An additional aspect of minimalist thought is the idea that the
derivation of syntactic structures should be uniform; that is, rules should not be stipulated as
applying at arbitrary points in a derivation, but instead apply throughout derivations. Minimalist
approaches to phrase structure have resulted in "Bare Phrase Structure," an attempt to eliminate
X-bar theory. In 1998, Chomsky suggested that derivations proceed in phases. The distinction of
Deep Structure vs. Surface Structure is not present in Minimalist theories of syntax, and the most
recent phase-based theories also eliminate LF and PF as unitary levels of representation.

[edit] Mathematical representation
Returning to the more general mathematical notion of a grammar, an important feature of all
transformational grammars is that they are more powerful than context-free grammars.[12] This
idea was formalized by Chomsky in the Chomsky hierarchy. Chomsky argued that it is
impossible to describe the structure of natural languages using context-free grammars.[13] His
general position regarding the non-context-freeness of natural language has held up since then,
although his specific examples regarding the inadequacy of CFGs in terms of their weak
generative capacity were later disproven.[14][15]

[edit] Transformations
The usual usage of the term 'transformation' in linguistics refers to a rule that takes an input
typically called the Deep Structure (in the Standard Theory) or D-structure (in the extended
standard theory or government and binding theory) and changes it in some restricted way to
result in a Surface Structure (or S-structure). In TGG, Deep structures were generated by a set of
phrase structure rules.

For example, a typical transformation in TG is the operation of subject-auxiliary inversion (SAI).
This rule takes as its input a declarative sentence with an auxiliary: "John has eaten all the
heirloom tomatoes." and transforms it into "Has John eaten all the heirloom tomatoes?" In their
original formulation (Chomsky 1957), these rules were stated as rules that held over strings of
either terminals or constituent symbols or both.

       X NP AUX Y        X AUX NP Y

(where NP = Noun Phrase and AUX = Auxiliary)

In the 1970s, by the time of the Extended Standard Theory, following the work of Joseph
Emonds on structure preservation, transformations came to be viewed as holding over trees. By
the end of government and binding theory in the late 1980s, transformations are no longer
structure changing operations at all; instead they add information to already existing trees by
copying constituents.

The earliest conceptions of transformations were that they were construction-specific devices.
For example, there was a transformation that turned active sentences into passive ones. A
different transformation raised embedded subjects into main clause subject position in sentences
such as "John seems to have gone"; and yet a third reordered arguments in the dative alternation.
With the shift from rules to principles and constraints that was found in the 1970s, these
construction-specific transformations morphed into general rules (all the examples just
mentioned being instances of NP movement), which eventually changed into the single general
rule of move alpha or Move.

Transformations actually come of two types: (i) the post-Deep structure kind mentioned above,
which are string or structure changing, and (ii) Generalized Transformations (GTs). Generalized
transformations were originally proposed in the earliest forms of generative grammar (e.g.,
Chomsky 1957). They take small structures, either atomic or generated by other rules, and
combine them. For example, the generalized transformation of embedding would take the kernel
"Dave said X" and the kernel "Dan likes smoking" and combine them into "Dave said Dan likes
smoking." GTs are thus structure building rather than structure changing. In the Extended
Standard Theory and government and binding theory, GTs were abandoned in favor of recursive
phrase structure rules. However, they are still present in tree-adjoining grammar as the
Substitution and Adjunction operations, and they have recently re-emerged in mainstream
generative grammar in Minimalism, as the operations Merge and Move.

In generative phonology, another form of transformation is the phonological rule, which
describes a mapping between an underlying representation (the phoneme) and the surface form
that is articulated during natural speech.[16]

[edit] See also
Antisymmetry
     Generalised phrase structure grammar
     Generative semantics
     Head-driven phrase structure grammar
     Heavy NP shift
     Lexical functional grammar
     Parasitic gap

[edit] References
  1. ^ Chomsky, Noam (1995). The Minimalist Program. MIT Press.
  2. ^ Chomsky, Noam (1965). Aspects of the Theory of Syntax. MIT Press.
      ISBN 0262530074.
  3. ^ The Port-Royal Grammar of 1660 identified similar principles; Chomsky, Noam
      (1972). Language and Mind. Harcourt Brace Jovanovich. ISBN 0151478104.
  4. ^ Jackendoff, Ray (1974). Semantic Interpretation in Generative Grammar. MIT Press.
      ISBN 0262100134.
  5. ^ May, Robert C. (1977). The Grammar of Quantification. MIT Phd Dissertation.
      ISBN 0824013921. (Supervised by Noam Chomsky, this dissertation introduced the idea
      of "logical form.")
  6. ^ Chomsky, Noam (1986). Knowledge of Language. New York:Praeger.
      ISBN 0275900258.
  7. ^ Chomsky, Noam (2001). "Derivation by Phase." In other words, in algebraic terms, the
      I-Language is the actual function, whereas the E-Language is the extension of this
      function. In Michael Kenstowicz (ed.) Ken Hale: A Life in Language. MIT Press. Pages
      1-52. (See p. 49 fn. 2 for comment on E-Language.)
  8. ^ Newmeyer, Frederick J. (1986). Linguistic Theory in America (Second Edition).
      Academic Press.
  9. ^ Chomsky, Noam (1995). The Minimalist Program. MIT Press. ISBN 0262531283.
  10. ^ Lappin, Shalom; Robert Levine and David Johnson (2000). "Topic ... Comment".
      Natural Language & Linguistic Theory 18 (3): 665–671. doi:10.1023/A:1006474128258.
  11. ^ Lappin, Shalom; Robert Levine and David Johnson (2001). "The Revolution
      Maximally Confused". Natural Language & Linguistic Theory 19 (4): 901–919.
      doi:10.1023/A:1013397516214.
  12. ^ Peters, Stanley; R. Ritchie (1973). "On the generative power of transformational
      grammars". Information Sciences 6: 49–83. doi:10.1016/0020-0255(73)90027-3.
  13. ^ Chomsky, Noam (1956). "Three models for the description of language". IRE
      Transactions on Information Theory 2 (3): 113–124. doi:10.1109/TIT.1956.1056813.
  14. ^ Shieber, Stuart (1985). "Evidence against the context-freeness of natural language".
      Linguistics and Philosophy 8 (3): 333–343. doi:10.1007/BF00630917.
  15. ^ Pullum, Geoffrey K.; Gerald Gazdar (1982). "Natural languages and context-free
      languages". Linguistics and Philosophy 4 (4): 471–504. doi:10.1007/BF00360802.
  16. ^ Goldsmith, John A (1995). "Phonological Theory". In John A. Goldsmith. The
      Handbook of Phonological Theory. Blackwell Handbooks in Linguistics. Blackwell
      Publishers. p. 2. ISBN 1405157682.
[edit] External links
         What is I-language? - Chapter 1 of I-language: An Introduction to Linguistics as
         Cognitive Science.
         The Syntax of Natural Language – an online textbook on transformational grammar.


Part-of-speech tagging
From Wikipedia, the free encyclopedia

 (Redirected from Part of speech tagger)

In corpus linguistics, part-of-speech tagging (POS tagging or POST), also called grammatical
tagging or word-category disambiguation, is the process of marking up the words in a text
(corpus) as corresponding to a particular part of speech, based on both its definition, as well as
its context —i.e. relationship with adjacent and related words in a phrase, sentence, or paragraph.
A simplified form of this is commonly taught to school-age children, in the identification of
words as nouns, verbs, adjectives, adverbs, etc.

Once performed by hand, POS tagging is now done in the context of computational linguistics,
using algorithms which associate discrete terms, as well as hidden parts of speech, in accordance
with a set of descriptive tags. POS-tagging algorithms fall into two distinctive groups: rule-based
and stochastic. E.Brill's tagger, one of the first and widely used English POS-taggers employs
rule based algorithms.


Contents
[hide]

         1 Principle
         2 History
              o 2.1 The Brown Corpus
              o 2.2 Use of Hidden Markov Models
              o 2.3 Dynamic Programming methods
              o 2.4 Unsupervised taggers
              o 2.5 Other taggers and methods
         3 Issues
         4 See also
         5 References
         6 ^ STAR POS-tagger
         7 External links



[edit] Principle
Part-of-speech tagging is harder than just having a list of words and their parts of speech,
because some words can represent more than one part of speech at different times, and because
some parts of speech are complex or unspoken. This is not rare—in natural languages (as
opposed to many artificial languages), a large percentage of word-forms are ambiguous. For
example, even "dogs", which is usually thought of as just a plural noun, can also be a verb:

       The sailor dogs the barmaid.

Performing grammatical tagging will indicate that "dogs" is a verb, and not the more common
plural noun, since one of the words must be the main verb, and the noun reading is less likely
following "sailor" (sailor !→ dogs). Semantic analysis can then extrapolate that "sailor" and
"barmaid" implicate "dogs" as 1) in the nautical context (sailor→<verb>←barmaid) and 2) an
action applied to the object "barmaid" ([subject] dogs→barmaid). In this context, "dogs" is a
nautical term meaning "fastens (a watertight barmaid) securely; applies a dog to".

"Dogged", on the other hand, can be either an adjective or a past-tense verb. Just which parts of
speech a word can represent varies greatly.

Native speakers of a language perform grammatical and semantic analysis innately, and thus
trained linguists can identify the grammatical parts of speech to various fine degrees depending
on the tagging system. Schools commonly teach that there are 9 parts of speech in English: noun,
verb, article, adjective, preposition, pronoun, adverb, conjunction, and interjection. However,
there are clearly many more categories and sub-categories. For nouns, plural, possessive, and
singular forms can be distinguished. In many languages words are also marked for their "case"
(role as subject, object, etc.), grammatical gender, and so on; while verbs are marked for tense,
aspect, and other things.

In part-of-speech tagging by computer, it is typical to distinguish from 50 to 150 separate parts
of speech for English, for example, NN for singular common nouns, NNS for plural common
nouns, NP for singular proper nouns (see the POS tags used in the Brown Corpus). Work on
stochastic methods for tagging Koine Greek (DeRose 1990) has used over 1,000 parts of speech,
and found that about as many words were ambiguous there as in English. A morphosyntactic
descriptor in the case of morphologically rich languages can be expressed like Ncmsan, which
means Category=Noun, Type = common, Gender = masculine, Number = singular, Case =
accusative, Animate = no.

[edit] History
[edit] The Brown Corpus

Research on part-of-speech tagging has been closely tied to corpus linguistics. The first major
corpus of English for computer analysis was the Brown Corpus developed at Brown University
by Henry Kucera and Nelson Francis, in the mid-1960s. It consists of about 1,000,000 words of
running English prose text, made up of 500 samples from randomly chosen publications. Each
sample is 2,000 or more words (ending at the first sentence-end after 2,000 words, so that the
corpus contains only complete sentences).
The Brown Corpus was painstakingly "tagged" with part-of-speech markers over many years. A
first approximation was done with a program by Greene and Rubin, which consisted of a huge
handmade list of what categories could co-occur at all. For example, article then noun can occur,
but article verb (arguably) cannot. The program got about 70% correct. Its results were
repeatedly reviewed and corrected by hand, and later users sent in errata, so that by the late 70s
the tagging was nearly perfect (allowing for some cases on which even human speakers might
not agree).

This corpus has been used for innumerable studies of word-frequency and of part-of-speech, and
inspired the development of similar "tagged" corpora in many other languages. Statistics derived
by analyzing it formed the basis for most later part-of-speech tagging systems, such as CLAWS
(linguistics) and VOLSUNGA. However, by this time (2005) it has been superseded by larger
corpora such as the 100 million word British National Corpus.

For some time, part-of-speech tagging was considered an inseparable part of natural language
processing, because there are certain cases where the correct part of speech cannot be decided
without understanding the semantics or even the pragmatics of the context. This is extremely
expensive, especially because analyzing the higher levels is much harder when multiple part-of-
speech possibilities must be considered for each word.

[edit] Use of Hidden Markov Models

In the mid 1980s, researchers in Europe began to use hidden Markov models (HMMs) to
disambiguate parts of speech, when working to tag the Lancaster-Oslo-Bergen Corpus of British
English. HMMs involve counting cases (such as from the Brown Corpus), and making a table of
the probabilities of certain sequences. For example, once you've seen an article such as 'the',
perhaps the next word is a noun 40% of the time, an adjective 40%, and a number 20%.
Knowing this, a program can decide that "can" in "the can" is far more likely to be a noun than a
verb or a modal. The same method can of course be used to benefit from knowledge about
following words.

More advanced ("higher order") HMMs learn the probabilities not only of pairs, but triples or
even larger sequences. So, for example, if you've just seen an article and a verb, the next item
may be very likely a preposition, article, or noun, but much less likely another verb.

When several ambiguous words occur together, the possibilities multiply. However, it is easy to
enumerate every combination and to assign a relative probability to each one, by multiplying
together the probabilities of each choice in turn. The combination with highest probability is then
chosen. The European group developed CLAWS, a tagging program that did exactly this, and
achieved accuracy in the 93-95% range.

It is worth remembering, as Eugene Charniak points out in Statistical techniques for natural
language parsing [1], that merely assigning the most common tag to each known word and the
tag "proper noun" to all unknowns, will approach 90% accuracy because many words are
unambiguous.
CLAWS pioneered the field of HMM-based part of speech tagging, but was quite expensive
since it enumerated all possibilities. It sometimes had to resort to backup methods when there
were simply too many (the Brown Corpus contains a case with 17 ambiguous words in a row,
and there are words such as "still" that can represent as many as 7 distinct parts of speech).

HMMs underlie the functioning of stochastic taggers and are used in various algorithms one of
the most widely used being the bi-directional inference algorithm [1].

[edit] Dynamic Programming methods

In 1987, Steven DeRose and Ken Church independently developed dynamic programming
algorithms to solve the same problem in vastly less time. Their methods were similar to the
Viterbi algorithm known for some time in other fields. DeRose used a table of pairs, while
Church used a table of triples and an ingenious method of estimating the values for triples that
were rare or nonexistent in the Brown Corpus (actual measurement of triple probabilities would
require a much larger corpus). Both methods achieved accuracy over 95%. DeRose's 1990
dissertation at Brown University included analyses of the specific error types, probabilities, and
other related data, and replicated his work for Greek, where it proved similarly effective.

These findings were surprisingly disruptive to the field of natural language processing. The
accuracy reported was higher than the typical accuracy of very sophisticated algorithms that
integrated part of speech choice with many higher levels of linguistic analysis: syntax,
morphology, semantics, and so on. CLAWS, DeRose's and Church's methods did fail for some of
the known cases where semantics is required, but those proved negligibly rare. This convinced
many in the field that part-of-speech tagging could usefully be separated out from the other
levels of processing; this in turn simplified the theory and practice of computerized language
analysis, and encouraged researchers to find ways to separate out other pieces as well. Markov
Models are now the standard method for part-of-speech assignment.

[edit] Unsupervised taggers

The methods already discussed involve working from a pre-existing corpus to learn tag
probabilities. It is, however, also possible to bootstrap using "unsupervised" tagging.
Unsupervised tagging techniques use an untagged corpus for their training data and produce the
tagset by induction. That is, they observe patterns in word use, and derive part-of-speech
categories themselves. For example, statistics readily reveal that "the", "a", and "an" occur in
similar contexts, while "eat" occurs in very different ones. With sufficient iteration, similarity
classes of words emerge that are remarkably similar to those human linguists would expect; and
the differences themselves sometimes suggest valuable new insights.[citation needed]

These two categories can be further subdivided into rule-based, stochastic, and neural
approaches.
[edit] Other taggers and methods

Some current major algorithms for part-of-speech tagging include the Viterbi algorithm, Brill
Tagger, Constraint Grammar, and the Baum-Welch algorithm (also known as the forward-
backward algorithm). Hidden Markov model and visible Markov model taggers can both be
implemented using the Viterbi algorithm.

Many machine learning methods have also been applied to the problem of POS tagging. Methods
such as SVM, Maximum entropy classifier, Perceptron, and Nearest-neighbor have all been tried,
and most can achieve accuracy above 95%.

A direct comparison of several methods is reported (with references) at [2]. This comparison
uses the Penn tag set on some of the Penn Treebank data, so the results are directly comparable.

However, many significant taggers are not included (perhaps because of the labor involved in
reconfiguring them for this particular dataset). Thus, it should not be assumed that the results
reported there are the best that can be achieved with a given approach; nor even the best that
have been achieved with a given approach.

[edit] Issues
While there is broad agreement about basic categories, a number of edge cases make it difficult
to settle on a single "correct" set of tags, even in a single language such as English. For example,
it is hard to say whether "fire" is functioning as an adjective or a noun in

 the big green fire truck

A second important example is the use/mention distinction, as in the following example, where
"blue" is clearly not functioning as an adjective (the Brown Corpus tag set appends the suffix "-
NC" in such cases):

 the word "blue" has 4 letters.

Words in a language other than that of the "main" text, are commonly tagged as "foreign",
usually in addition to a tag for the role the foreign word is actually playing in context.

There are also many cases where POS categories and "words" do not map one to one, for
example:

 David's
 gonna
 don't
 vice versa
 first-cut
 cannot
 pre- and post-secondary
 look (a word) up
In the last example, "look" and "up" arguably function as a single verbal unit, despite the
possibility of other words coming between them. Some tag sets (such as Penn) break hyphenated
words, contractions, and possessives into separate tokens, thus avoiding some but far from all
such problems.

It is unclear whether it is best to treat words such as "be", "have", and "do" as categories in their
own right (as in the Brown Corpus), or as simply verbs (as in the LOB Corpus and the Penn
Treebank). "be" has more forms than other English verbs, and occurs in quite different
grammatical contexts, complicating the issue.

The most popular "tag set" for POS tagging for American English is probably the Penn tag set,
developed in the Penn Treebank project. It is largely similar to the earlier Brown Corpus and
LOB Corpus tag sets, though much smaller. In Europe, tag sets from the Eagles Guidelines see
wide use, and include versions for multiple languages.

POS tagging work has been done in a variety of languages, and the set of POS tags used varies
greatly with language. Tags usually are designed to include overt morphological distinctions
(this makes the tag sets for heavily inflected languages such as Greek and Latin very large; and
makes tagging words in agglutinative languages such an Inuit virtually impossible. However,
Petrov, D. Das, and R. McDonald ("A Universal Part-of-Speech Tagset"
http://arxiv.org/abs/1104.2086) have proposed a "universal" tag set, with 12 categories (for
example, no subtypes of nouns, verbs, punctuation, etc; no distinction of "to" as an infinitive
marker vs. preposition, etc). Whether a very small set of very broad tags, or a much larger set of
more precise ones, is preferable, depends on the purpose at hand. Automatic tagging is easier on
smaller tag-sets.

[edit] See also
       Semantic net
       Sliding window based part-of-speech tagging
       Trigram tagger
       Word sense disambiguation


[edit] References
       Charniak, Eugene. 1997. "Statistical Techniques for Natural Language Parsing". AI Magazine
       18(4):33–44.
       Hans van Halteren, Jakub Zavrel, Walter Daelemans. 2001. Improving Accuracy in NLP Through
       Combination of Machine Learning Systems. Computational Linguistics. 27(2): 199–229. PDF
       DeRose, Steven J. 1990. "Stochastic Methods for Resolution of Grammatical Category Ambiguity
       in Inflected and Uninflected Languages." Ph.D. Dissertation. Providence, RI: Brown University
       Department of Cognitive and Linguistic Sciences.
       DeRose, Steven J. 1988. "Grammatical category disambiguation by statistical optimization."
       Computational Linguistics 14(1): 31–39. [3]
[edit]
  1. ^ STAR POS-tagger


[edit] External links
     Overview of available taggers
     Cypher A natural language transcoder that performs POS-tagging, morphological processing,
     lexical analysis, to produce RDF and SPARQL from natural language BROKEN LINK
     Resources for Studying English Syntax Online
     CLAWS
     LingPipe Commercial Java natural language processing software including trainable part-of-
     speech taggers with first-best, n-best and per-tag confidence output.
     OpenNLP Tagger AL 2.0 Tagger based on maxent and perceptron classifiers
     CRFTagger Conditional Random Fields (CRFs) English POS Tagger
     JTextPro A Java-based Text Processing Toolkit
     Citar LGPL C++ Hidden Markov Model trigram POS tagger, a Java port named Jitar is also
     available
     Ninja-PoST PHP port of GPoSTTL, based on Eric Brill's rule-based tagger
     ComplexityIntelligence, LLC Free and Commercial NLP Web Services for Part Of Speech Tagging
     (and Named Entity Recognition)
     Part-of-Speech tagging based on Soundex features
     FastTag - LGPL Java POS tagger based on Eric Brill's rule-based tagger
     jspos - LGPL Javascript port of FastTag
     Topia TermExtractor - Python implementation of the UPenn BioIE parts-of-speech algorithm

More Related Content

What's hot

Corpus linguistics the basics
Corpus linguistics the basicsCorpus linguistics the basics
Corpus linguistics the basicsJorge Baptista
 
SAPIRWHORF HYPOTHEIS
SAPIRWHORF HYPOTHEISSAPIRWHORF HYPOTHEIS
SAPIRWHORF HYPOTHEISRajputt Ainee
 
Transformational generative grammar
Transformational generative grammarTransformational generative grammar
Transformational generative grammarAliImran376
 
Transformational Grammar
Transformational GrammarTransformational Grammar
Transformational GrammarCristina Tamayo
 
Applied linguistics presentation
Applied linguistics  presentationApplied linguistics  presentation
Applied linguistics presentationMuhammad Furqan
 
Transformational generative grammar
Transformational  generative grammarTransformational  generative grammar
Transformational generative grammarBaishakhi Amin
 
Linguistics vs applied linguistics
Linguistics vs applied linguisticsLinguistics vs applied linguistics
Linguistics vs applied linguisticsUTPL UTPL
 
Principles of parameters
Principles of parametersPrinciples of parameters
Principles of parametersVelnar
 
Language standardization: How and why
Language standardization: How and whyLanguage standardization: How and why
Language standardization: How and whyadm-2012
 
Structuralism in linguistics
Structuralism in linguisticsStructuralism in linguistics
Structuralism in linguisticsSadaqat Hussain
 
Transformational Generative Grammar
Transformational Generative GrammarTransformational Generative Grammar
Transformational Generative GrammarHani Khan
 
Optimality theory.pptx
Optimality theory.pptxOptimality theory.pptx
Optimality theory.pptxamjadnaasir
 
Cognitive Approaches to Second Language Acquisition
Cognitive Approaches to Second Language AcquisitionCognitive Approaches to Second Language Acquisition
Cognitive Approaches to Second Language AcquisitionOla Sayed Ahmed
 
Language Planning
Language PlanningLanguage Planning
Language PlanningAyesha Mir
 

What's hot (20)

Corpus linguistics the basics
Corpus linguistics the basicsCorpus linguistics the basics
Corpus linguistics the basics
 
SAPIRWHORF HYPOTHEIS
SAPIRWHORF HYPOTHEISSAPIRWHORF HYPOTHEIS
SAPIRWHORF HYPOTHEIS
 
Transformational generative grammar
Transformational generative grammarTransformational generative grammar
Transformational generative grammar
 
Stylistics
Stylistics Stylistics
Stylistics
 
Transformational Grammar
Transformational GrammarTransformational Grammar
Transformational Grammar
 
Applied linguistics presentation
Applied linguistics  presentationApplied linguistics  presentation
Applied linguistics presentation
 
Transformational generative grammar
Transformational  generative grammarTransformational  generative grammar
Transformational generative grammar
 
Systemic Functional Linguistics
Systemic Functional LinguisticsSystemic Functional Linguistics
Systemic Functional Linguistics
 
Functionalism
FunctionalismFunctionalism
Functionalism
 
Linguistics vs applied linguistics
Linguistics vs applied linguisticsLinguistics vs applied linguistics
Linguistics vs applied linguistics
 
Principles of parameters
Principles of parametersPrinciples of parameters
Principles of parameters
 
Language standardization: How and why
Language standardization: How and whyLanguage standardization: How and why
Language standardization: How and why
 
Structuralism in linguistics
Structuralism in linguisticsStructuralism in linguistics
Structuralism in linguistics
 
Transformational Generative Grammar
Transformational Generative GrammarTransformational Generative Grammar
Transformational Generative Grammar
 
Generative grammar
Generative grammarGenerative grammar
Generative grammar
 
Optimality theory.pptx
Optimality theory.pptxOptimality theory.pptx
Optimality theory.pptx
 
Universal grammar
Universal grammarUniversal grammar
Universal grammar
 
Cognitive Approaches to Second Language Acquisition
Cognitive Approaches to Second Language AcquisitionCognitive Approaches to Second Language Acquisition
Cognitive Approaches to Second Language Acquisition
 
X bar theory
X bar theoryX bar theory
X bar theory
 
Language Planning
Language PlanningLanguage Planning
Language Planning
 

Viewers also liked

Transformational Grammar by: Noam Chomsky
Transformational Grammar by: Noam ChomskyTransformational Grammar by: Noam Chomsky
Transformational Grammar by: Noam ChomskyShiela May Claro
 
Transformations in Transformational Generative Grammar
Transformations in Transformational Generative GrammarTransformations in Transformational Generative Grammar
Transformations in Transformational Generative GrammarBayu Jaka Magistra
 
Transformational grammar
Transformational grammarTransformational grammar
Transformational grammarJack Feng
 
Transformational generative grammar
Transformational generative grammarTransformational generative grammar
Transformational generative grammarKat OngCan
 
Presentation generative-transformational grammar
Presentation generative-transformational grammar Presentation generative-transformational grammar
Presentation generative-transformational grammar Nailun Naja
 
Generative grammar
Generative grammarGenerative grammar
Generative grammarLheo Fronda
 
Summary - Transformational-Generative Theory
Summary - Transformational-Generative TheorySummary - Transformational-Generative Theory
Summary - Transformational-Generative TheoryMarielis VI
 

Viewers also liked (9)

Transformational Grammar by: Noam Chomsky
Transformational Grammar by: Noam ChomskyTransformational Grammar by: Noam Chomsky
Transformational Grammar by: Noam Chomsky
 
Transformations in Transformational Generative Grammar
Transformations in Transformational Generative GrammarTransformations in Transformational Generative Grammar
Transformations in Transformational Generative Grammar
 
Transformational grammar
Transformational grammarTransformational grammar
Transformational grammar
 
Transformational generative grammar
Transformational generative grammarTransformational generative grammar
Transformational generative grammar
 
Presentation generative-transformational grammar
Presentation generative-transformational grammar Presentation generative-transformational grammar
Presentation generative-transformational grammar
 
X bar schema
X bar schemaX bar schema
X bar schema
 
Generative grammar
Generative grammarGenerative grammar
Generative grammar
 
Transformational Generative Grammar
Transformational Generative GrammarTransformational Generative Grammar
Transformational Generative Grammar
 
Summary - Transformational-Generative Theory
Summary - Transformational-Generative TheorySummary - Transformational-Generative Theory
Summary - Transformational-Generative Theory
 

Similar to Transformational grammar

Avram noam chomsky's services to syntax.
Avram noam chomsky's services to syntax.Avram noam chomsky's services to syntax.
Avram noam chomsky's services to syntax.Nabeela Taimur Ali
 
contributions of lexicography and corpus linguistics to a theory of language ...
contributions of lexicography and corpus linguistics to a theory of language ...contributions of lexicography and corpus linguistics to a theory of language ...
contributions of lexicography and corpus linguistics to a theory of language ...ayfa
 
Colaborative work Transformational grammar
Colaborative work Transformational grammarColaborative work Transformational grammar
Colaborative work Transformational grammarDaysi Pachacama
 
IMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGE
IMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGEIMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGE
IMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGEJamie Boyd
 
Applied linguistics 1=class 1
Applied linguistics 1=class 1Applied linguistics 1=class 1
Applied linguistics 1=class 1Jordán Masías
 
melt104-functionalgrammar-121027003950-phpapp02.pdf
melt104-functionalgrammar-121027003950-phpapp02.pdfmelt104-functionalgrammar-121027003950-phpapp02.pdf
melt104-functionalgrammar-121027003950-phpapp02.pdfAliAwan652291
 
Linguistics and language
Linguistics and languageLinguistics and language
Linguistics and languagetahajoon
 
теория грамматики.pptx
теория грамматики.pptxтеория грамматики.pptx
теория грамматики.pptxZhazgul Kachkynbekova
 
. . . all human languages do share the same structure. More e.docx
. . . all human languages do share the same structure. More e.docx. . . all human languages do share the same structure. More e.docx
. . . all human languages do share the same structure. More e.docxadkinspaige22
 
. . . all human languages do share the same structure. More e.docx
 . . . all human languages do share the same structure. More e.docx . . . all human languages do share the same structure. More e.docx
. . . all human languages do share the same structure. More e.docxShiraPrater50
 
Cuestionario Linguistica Aplicada
Cuestionario Linguistica AplicadaCuestionario Linguistica Aplicada
Cuestionario Linguistica AplicadaJordán Masías
 
Linguistic theories approaches and methods
Linguistic theories approaches and methodsLinguistic theories approaches and methods
Linguistic theories approaches and methodsEsraaAlobali
 
Introduction of Michael Alexander Kirkwood Halliday.
Introduction of Michael Alexander Kirkwood Halliday.Introduction of Michael Alexander Kirkwood Halliday.
Introduction of Michael Alexander Kirkwood Halliday.AleeenaFarooq
 
Definition of terms
Definition of termsDefinition of terms
Definition of termsmabieeee21
 
Linguistic approach by sheena bernal
Linguistic approach by sheena bernalLinguistic approach by sheena bernal
Linguistic approach by sheena bernalEdi sa puso mo :">
 

Similar to Transformational grammar (20)

Avram noam chomsky's services to syntax.
Avram noam chomsky's services to syntax.Avram noam chomsky's services to syntax.
Avram noam chomsky's services to syntax.
 
contributions of lexicography and corpus linguistics to a theory of language ...
contributions of lexicography and corpus linguistics to a theory of language ...contributions of lexicography and corpus linguistics to a theory of language ...
contributions of lexicography and corpus linguistics to a theory of language ...
 
General linguistics 1
General linguistics 1General linguistics 1
General linguistics 1
 
Colaborative work Transformational grammar
Colaborative work Transformational grammarColaborative work Transformational grammar
Colaborative work Transformational grammar
 
IMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGE
IMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGEIMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGE
IMPORTANCE OF LINGUISTICS IN ENGLISH LANGUAGE
 
Applied linguistics 1=class 1
Applied linguistics 1=class 1Applied linguistics 1=class 1
Applied linguistics 1=class 1
 
Minimalism.pptx
Minimalism.pptxMinimalism.pptx
Minimalism.pptx
 
melt104-functionalgrammar-121027003950-phpapp02.pdf
melt104-functionalgrammar-121027003950-phpapp02.pdfmelt104-functionalgrammar-121027003950-phpapp02.pdf
melt104-functionalgrammar-121027003950-phpapp02.pdf
 
MELT 104 Functional Grammar
MELT 104   Functional GrammarMELT 104   Functional Grammar
MELT 104 Functional Grammar
 
Linguistics and language
Linguistics and languageLinguistics and language
Linguistics and language
 
теория грамматики.pptx
теория грамматики.pptxтеория грамматики.pptx
теория грамматики.pptx
 
. . . all human languages do share the same structure. More e.docx
. . . all human languages do share the same structure. More e.docx. . . all human languages do share the same structure. More e.docx
. . . all human languages do share the same structure. More e.docx
 
. . . all human languages do share the same structure. More e.docx
 . . . all human languages do share the same structure. More e.docx . . . all human languages do share the same structure. More e.docx
. . . all human languages do share the same structure. More e.docx
 
Cuestionario Linguistica Aplicada
Cuestionario Linguistica AplicadaCuestionario Linguistica Aplicada
Cuestionario Linguistica Aplicada
 
Linguistic theories approaches and methods
Linguistic theories approaches and methodsLinguistic theories approaches and methods
Linguistic theories approaches and methods
 
Introduction of Michael Alexander Kirkwood Halliday.
Introduction of Michael Alexander Kirkwood Halliday.Introduction of Michael Alexander Kirkwood Halliday.
Introduction of Michael Alexander Kirkwood Halliday.
 
Definition of terms
Definition of termsDefinition of terms
Definition of terms
 
Functional grammar
Functional grammarFunctional grammar
Functional grammar
 
Linguistic approach by sheena bernal
Linguistic approach by sheena bernalLinguistic approach by sheena bernal
Linguistic approach by sheena bernal
 
B2120911.pdf
B2120911.pdfB2120911.pdf
B2120911.pdf
 

More from Jasline Presilda (20)

I6 mala3 sowmya
I6 mala3 sowmyaI6 mala3 sowmya
I6 mala3 sowmya
 
I5 geetha4 suraiya
I5 geetha4 suraiyaI5 geetha4 suraiya
I5 geetha4 suraiya
 
I4 madankarky3 subalalitha
I4 madankarky3 subalalithaI4 madankarky3 subalalitha
I4 madankarky3 subalalitha
 
I3 madankarky2 karthika
I3 madankarky2 karthikaI3 madankarky2 karthika
I3 madankarky2 karthika
 
I2 madankarky1 jharibabu
I2 madankarky1 jharibabuI2 madankarky1 jharibabu
I2 madankarky1 jharibabu
 
I1 geetha3 revathi
I1 geetha3 revathiI1 geetha3 revathi
I1 geetha3 revathi
 
Hari tamil-complete details
Hari tamil-complete detailsHari tamil-complete details
Hari tamil-complete details
 
H4 neelavathy
H4 neelavathyH4 neelavathy
H4 neelavathy
 
H3 anuraj
H3 anurajH3 anuraj
H3 anuraj
 
H2 gunasekaran
H2 gunasekaranH2 gunasekaran
H2 gunasekaran
 
H1 iniya nehru
H1 iniya nehruH1 iniya nehru
H1 iniya nehru
 
G3 chandrakala
G3 chandrakalaG3 chandrakala
G3 chandrakala
 
G2 selvakumar
G2 selvakumarG2 selvakumar
G2 selvakumar
 
G1 nmurugaiyan
G1 nmurugaiyanG1 nmurugaiyan
G1 nmurugaiyan
 
Front matter
Front matterFront matter
Front matter
 
F2 pvairam sarathy
F2 pvairam sarathyF2 pvairam sarathy
F2 pvairam sarathy
 
F1 ferdinjoe
F1 ferdinjoeF1 ferdinjoe
F1 ferdinjoe
 
Emerging
EmergingEmerging
Emerging
 
E3 ilangkumaran
E3 ilangkumaranE3 ilangkumaran
E3 ilangkumaran
 
E2 tamilselvan
E2 tamilselvanE2 tamilselvan
E2 tamilselvan
 

Recently uploaded

Ultra structure and life cycle of Plasmodium.pptx
Ultra structure and life cycle of Plasmodium.pptxUltra structure and life cycle of Plasmodium.pptx
Ultra structure and life cycle of Plasmodium.pptxDr. Asif Anas
 
CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...
CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...
CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...Nguyen Thanh Tu Collection
 
The basics of sentences session 10pptx.pptx
The basics of sentences session 10pptx.pptxThe basics of sentences session 10pptx.pptx
The basics of sentences session 10pptx.pptxheathfieldcps1
 
How to Add Existing Field in One2Many Tree View in Odoo 17
How to Add Existing Field in One2Many Tree View in Odoo 17How to Add Existing Field in One2Many Tree View in Odoo 17
How to Add Existing Field in One2Many Tree View in Odoo 17Celine George
 
Practical Research 1: Lesson 8 Writing the Thesis Statement.pptx
Practical Research 1: Lesson 8 Writing the Thesis Statement.pptxPractical Research 1: Lesson 8 Writing the Thesis Statement.pptx
Practical Research 1: Lesson 8 Writing the Thesis Statement.pptxKatherine Villaluna
 
Clinical Pharmacy Introduction to Clinical Pharmacy, Concept of clinical pptx
Clinical Pharmacy  Introduction to Clinical Pharmacy, Concept of clinical pptxClinical Pharmacy  Introduction to Clinical Pharmacy, Concept of clinical pptx
Clinical Pharmacy Introduction to Clinical Pharmacy, Concept of clinical pptxraviapr7
 
UKCGE Parental Leave Discussion March 2024
UKCGE Parental Leave Discussion March 2024UKCGE Parental Leave Discussion March 2024
UKCGE Parental Leave Discussion March 2024UKCGE
 
AUDIENCE THEORY -- FANDOM -- JENKINS.pptx
AUDIENCE THEORY -- FANDOM -- JENKINS.pptxAUDIENCE THEORY -- FANDOM -- JENKINS.pptx
AUDIENCE THEORY -- FANDOM -- JENKINS.pptxiammrhaywood
 
How to Show Error_Warning Messages in Odoo 17
How to Show Error_Warning Messages in Odoo 17How to Show Error_Warning Messages in Odoo 17
How to Show Error_Warning Messages in Odoo 17Celine George
 
Education and training program in the hospital APR.pptx
Education and training program in the hospital APR.pptxEducation and training program in the hospital APR.pptx
Education and training program in the hospital APR.pptxraviapr7
 
Philosophy of Education and Educational Philosophy
Philosophy of Education  and Educational PhilosophyPhilosophy of Education  and Educational Philosophy
Philosophy of Education and Educational PhilosophyShuvankar Madhu
 
HED Office Sohayok Exam Question Solution 2023.pdf
HED Office Sohayok Exam Question Solution 2023.pdfHED Office Sohayok Exam Question Solution 2023.pdf
HED Office Sohayok Exam Question Solution 2023.pdfMohonDas
 
How to Solve Singleton Error in the Odoo 17
How to Solve Singleton Error in the  Odoo 17How to Solve Singleton Error in the  Odoo 17
How to Solve Singleton Error in the Odoo 17Celine George
 
What is the Future of QuickBooks DeskTop?
What is the Future of QuickBooks DeskTop?What is the Future of QuickBooks DeskTop?
What is the Future of QuickBooks DeskTop?TechSoup
 
Quality Assurance_GOOD LABORATORY PRACTICE
Quality Assurance_GOOD LABORATORY PRACTICEQuality Assurance_GOOD LABORATORY PRACTICE
Quality Assurance_GOOD LABORATORY PRACTICESayali Powar
 
5 charts on South Africa as a source country for international student recrui...
5 charts on South Africa as a source country for international student recrui...5 charts on South Africa as a source country for international student recrui...
5 charts on South Africa as a source country for international student recrui...CaraSkikne1
 
PISA-VET launch_El Iza Mohamedou_19 March 2024.pptx
PISA-VET launch_El Iza Mohamedou_19 March 2024.pptxPISA-VET launch_El Iza Mohamedou_19 March 2024.pptx
PISA-VET launch_El Iza Mohamedou_19 March 2024.pptxEduSkills OECD
 
CAULIFLOWER BREEDING 1 Parmar pptx
CAULIFLOWER BREEDING 1 Parmar pptxCAULIFLOWER BREEDING 1 Parmar pptx
CAULIFLOWER BREEDING 1 Parmar pptxSaurabhParmar42
 
CapTechU Doctoral Presentation -March 2024 slides.pptx
CapTechU Doctoral Presentation -March 2024 slides.pptxCapTechU Doctoral Presentation -March 2024 slides.pptx
CapTechU Doctoral Presentation -March 2024 slides.pptxCapitolTechU
 
M-2- General Reactions of amino acids.pptx
M-2- General Reactions of amino acids.pptxM-2- General Reactions of amino acids.pptx
M-2- General Reactions of amino acids.pptxDr. Santhosh Kumar. N
 

Recently uploaded (20)

Ultra structure and life cycle of Plasmodium.pptx
Ultra structure and life cycle of Plasmodium.pptxUltra structure and life cycle of Plasmodium.pptx
Ultra structure and life cycle of Plasmodium.pptx
 
CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...
CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...
CHUYÊN ĐỀ DẠY THÊM TIẾNG ANH LỚP 11 - GLOBAL SUCCESS - NĂM HỌC 2023-2024 - HK...
 
The basics of sentences session 10pptx.pptx
The basics of sentences session 10pptx.pptxThe basics of sentences session 10pptx.pptx
The basics of sentences session 10pptx.pptx
 
How to Add Existing Field in One2Many Tree View in Odoo 17
How to Add Existing Field in One2Many Tree View in Odoo 17How to Add Existing Field in One2Many Tree View in Odoo 17
How to Add Existing Field in One2Many Tree View in Odoo 17
 
Practical Research 1: Lesson 8 Writing the Thesis Statement.pptx
Practical Research 1: Lesson 8 Writing the Thesis Statement.pptxPractical Research 1: Lesson 8 Writing the Thesis Statement.pptx
Practical Research 1: Lesson 8 Writing the Thesis Statement.pptx
 
Clinical Pharmacy Introduction to Clinical Pharmacy, Concept of clinical pptx
Clinical Pharmacy  Introduction to Clinical Pharmacy, Concept of clinical pptxClinical Pharmacy  Introduction to Clinical Pharmacy, Concept of clinical pptx
Clinical Pharmacy Introduction to Clinical Pharmacy, Concept of clinical pptx
 
UKCGE Parental Leave Discussion March 2024
UKCGE Parental Leave Discussion March 2024UKCGE Parental Leave Discussion March 2024
UKCGE Parental Leave Discussion March 2024
 
AUDIENCE THEORY -- FANDOM -- JENKINS.pptx
AUDIENCE THEORY -- FANDOM -- JENKINS.pptxAUDIENCE THEORY -- FANDOM -- JENKINS.pptx
AUDIENCE THEORY -- FANDOM -- JENKINS.pptx
 
How to Show Error_Warning Messages in Odoo 17
How to Show Error_Warning Messages in Odoo 17How to Show Error_Warning Messages in Odoo 17
How to Show Error_Warning Messages in Odoo 17
 
Education and training program in the hospital APR.pptx
Education and training program in the hospital APR.pptxEducation and training program in the hospital APR.pptx
Education and training program in the hospital APR.pptx
 
Philosophy of Education and Educational Philosophy
Philosophy of Education  and Educational PhilosophyPhilosophy of Education  and Educational Philosophy
Philosophy of Education and Educational Philosophy
 
HED Office Sohayok Exam Question Solution 2023.pdf
HED Office Sohayok Exam Question Solution 2023.pdfHED Office Sohayok Exam Question Solution 2023.pdf
HED Office Sohayok Exam Question Solution 2023.pdf
 
How to Solve Singleton Error in the Odoo 17
How to Solve Singleton Error in the  Odoo 17How to Solve Singleton Error in the  Odoo 17
How to Solve Singleton Error in the Odoo 17
 
What is the Future of QuickBooks DeskTop?
What is the Future of QuickBooks DeskTop?What is the Future of QuickBooks DeskTop?
What is the Future of QuickBooks DeskTop?
 
Quality Assurance_GOOD LABORATORY PRACTICE
Quality Assurance_GOOD LABORATORY PRACTICEQuality Assurance_GOOD LABORATORY PRACTICE
Quality Assurance_GOOD LABORATORY PRACTICE
 
5 charts on South Africa as a source country for international student recrui...
5 charts on South Africa as a source country for international student recrui...5 charts on South Africa as a source country for international student recrui...
5 charts on South Africa as a source country for international student recrui...
 
PISA-VET launch_El Iza Mohamedou_19 March 2024.pptx
PISA-VET launch_El Iza Mohamedou_19 March 2024.pptxPISA-VET launch_El Iza Mohamedou_19 March 2024.pptx
PISA-VET launch_El Iza Mohamedou_19 March 2024.pptx
 
CAULIFLOWER BREEDING 1 Parmar pptx
CAULIFLOWER BREEDING 1 Parmar pptxCAULIFLOWER BREEDING 1 Parmar pptx
CAULIFLOWER BREEDING 1 Parmar pptx
 
CapTechU Doctoral Presentation -March 2024 slides.pptx
CapTechU Doctoral Presentation -March 2024 slides.pptxCapTechU Doctoral Presentation -March 2024 slides.pptx
CapTechU Doctoral Presentation -March 2024 slides.pptx
 
M-2- General Reactions of amino acids.pptx
M-2- General Reactions of amino acids.pptxM-2- General Reactions of amino acids.pptx
M-2- General Reactions of amino acids.pptx
 

Transformational grammar

  • 1. Transformational grammar From Wikipedia, the free encyclopedia In linguistics, a transformational grammar or transformational-generative grammar (TGG) is a generative grammar, especially of a natural language, that has been developed in a Chomskyan tradition. Additionally, transformational grammar is the Chomskyan tradition that gives rise to specific transformational grammars. Much current research in transformational grammar is inspired by Chomsky's Minimalist Program.[1] Contents [hide] 1 Deep structure and surface structure 2 Development of basic concepts 3 Innate linguistic knowledge 4 Grammatical theories 5 "I-Language" and "E-Language" 6 Grammaticality 7 Minimalism 8 Mathematical representation 9 Transformations 10 See also 11 References 12 External links [edit] Deep structure and surface structure Linguistics Theoretical linguistics Cognitive linguistics
  • 2. Generative linguistics Functional theories of grammar Quantitative linguistics Phonology · Graphemics Morphology · Syntax · Lexis Semantics · Pragmatics Descriptive linguistics Anthropological linguistics Comparative linguistics Historical linguistics Phonetics · Graphetics Etymology · Sociolinguistics Applied and experimental linguistics Computational linguistics Evolutionary linguistics Forensic linguistics Internet linguistics Language acquisition Language assessment Language development Language education Linguistic anthropology Neurolinguistics Psycholinguistics Second language acquisition Related articles History of linguistics Linguistic prescription
  • 3. List of linguists List of unsolved problems in linguistics Portal v·d·e In 1957, Noam Chomsky published Syntactic Structures, in which he developed the idea that each sentence in a language has two levels of representation — a deep structure and a surface structure.[2][3] The deep structure represented the core semantic relations of a sentence, and was mapped on to the surface structure (which followed the phonological form of the sentence very closely) via transformations. Chomsky believed there are considerable similarities between languages' deep structures, and that these structures reveal properties, common to all languages that surface structures conceal. However, this may not have been the central motivation for introducing deep structure. Transformations had been proposed prior to the development of deep structure as a means of increasing the mathematical and descriptive power of context-free grammars. Similarly, deep structure was devised largely for technical reasons relating to early semantic theory. Chomsky emphasizes the importance of modern formal mathematical devices in the development of grammatical theory: But the fundamental reason for [the] inadequacy of traditional grammars is a more technical one. Although it was well understood that linguistic processes are in some sense "creative," the technical devices for expressing a system of recursive processes were simply not available until much more recently. In fact, a real understanding of how a language can (in Humboldt's words) "make infinite use of finite means" has developed only within the last thirty years, in the course of studies in the foundations of mathematics. —Aspects of the Theory of Syntax [edit] Development of basic concepts Though transformations continue to be important in Chomsky's current theories, he has now abandoned the original notion of Deep Structure and Surface Structure. Initially, two additional levels of representation were introduced (LF — Logical Form, and PF — Phonetic Form), and then in the 1990s Chomsky sketched out a new program of research known as Minimalism, in which Deep Structure and Surface Structure no longer featured and PF and LF remained as the only levels of representation. To complicate the understanding of the development of Noam Chomsky's theories, the precise meanings of Deep Structure and Surface Structure have changed over time — by the 1970s, the two were normally referred to simply as D-Structure and S-Structure by Chomskyan linguists. In
  • 4. particular, the idea that the meaning of a sentence was determined by its Deep Structure (taken to its logical conclusions by the generative semanticists during the same period) was dropped for good by Chomskyan linguists when LF took over this role (previously, Chomsky and Ray Jackendoff had begun to argue that meaning was determined by both Deep and Surface Structure).[4][5] [edit] Innate linguistic knowledge Terms such as "transformation" can give the impression that theories of transformational generative grammar are intended as a model for the processes through which the human mind constructs and understands sentences. Chomsky is clear that this is not in fact the case: a generative grammar models only the knowledge that underlies the human ability to speak and understand. One of the most important of Chomsky's ideas is that most of this knowledge is innate, with the result that a baby can have a large body of prior knowledge about the structure of language in general, and need only actually learn the idiosyncratic features of the language(s) it is exposed to. Chomsky was not the first person to suggest that all languages had certain fundamental things in common (he quotes philosophers writing several centuries ago who had the same basic idea), but he helped to make the innateness theory respectable after a period dominated by more behaviorist attitudes towards language. Perhaps more significantly, he made concrete and technically sophisticated proposals about the structure of language, and made important proposals regarding how the success of grammatical theories should be evaluated. [edit] Grammatical theories In the 1960s, Chomsky introduced two central ideas relevant to the construction and evaluation of grammatical theories. The first was the distinction between competence and performance. Chomsky noted the obvious fact that people, when speaking in the real world, often make linguistic errors (e.g., starting a sentence and then abandoning it midway through). He argued that these errors in linguistic performance were irrelevant to the study of linguistic competence (the knowledge that allows people to construct and understand grammatical sentences). Consequently, the linguist can study an idealised version of language, greatly simplifying linguistic analysis (see the "Grammaticality" section below). The second idea related directly to the evaluation of theories of grammar. Chomsky distinguished between grammars that achieve descriptive adequacy and those that go further and achieved explanatory adequacy. A descriptively adequate grammar for a particular language defines the (infinite) set of grammatical sentences in that language; that is, it describes the language in its entirety. A grammar that achieves explanatory adequacy has the additional property that it gives an insight into the underlying linguistic structures in the human mind; that is, it does not merely describe the grammar of a language, but makes predictions about how linguistic knowledge is mentally represented. For Chomsky, the nature of such mental representations is largely innate, so if a grammatical theory has explanatory adequacy it must be able to explain the various grammatical nuances of the languages of the world as relatively minor variations in the universal pattern of human language. Chomsky argued that, even though linguists were still a long way from constructing descriptively adequate grammars, progress in terms of descriptive adequacy will only come if linguists hold explanatory adequacy as their goal. In other words, real insight into
  • 5. the structure of individual languages can only be gained through comparative study of a wide range of languages, on the assumption that they are all cut from the same cloth. [edit] "I-Language" and "E-Language" In 1986, Chomsky proposed a distinction between I-Language and E-Language, similar but not identical to the competence/performance distinction.[6] (I-language) refers to Internal language and is contrasted with External Language (or E-language). I-Language is taken to be the object of study in linguistic theory; it is the mentally represented linguistic knowledge that a native speaker of a language has, and is therefore a mental object — from this perspective, most of theoretical linguistics is a branch of psychology. E-Language encompasses all other notions of what a language is, for example that it is a body of knowledge or behavioural habits shared by a community. Thus, E-Language is not itself a coherent concept,[7] and Chomsky argues that such notions of language are not useful in the study of innate linguistic knowledge, i.e., competence, even though they may seem sensible and intuitive, and useful in other areas of study. Competence, he argues, can only be studied if languages are treated as mental objects. [edit] Grammaticality Further information: Grammaticality Chomsky argued that the notions "grammatical" and "ungrammatical" could be defined in a meaningful and useful way. In contrast, an extreme behaviorist linguist would argue that language can only be studied through recordings or transcriptions of actual speech, the role of the linguist being to look for patterns in such observed speech, but not to hypothesize about why such patterns might occur, nor to label particular utterances as either "grammatical" or "ungrammatical." Although few linguists in the 1950s actually took such an extreme position, Chomsky was at an opposite extreme, defining grammaticality in an unusually mentalistic way (for the time).[8] He argued that the intuition of a native speaker is enough to define the grammaticalness of a sentence; that is, if a particular string of English words elicits a double take, or feeling of wrongness in a native English speaker, and when various extraneous factors affecting intuitions are controlled for, it can be said that the string of words is ungrammatical. This, according to Chomsky, is entirely distinct from the question of whether a sentence is meaningful, or can be understood. It is possible for a sentence to be both grammatical and meaningless, as in Chomsky's famous example "colorless green ideas sleep furiously." But such sentences manifest a linguistic problem distinct from that posed by meaningful but ungrammatical (non)-sentences such as "man the bit sandwich the," the meaning of which is fairly clear, but no native speaker would accept as well formed. The use of such intuitive judgments permitted generative syntacticians to base their research on a methodology in which studying language through a corpus of observed speech became downplayed, since the grammatical properties of constructed sentences were considered to be appropriate data to build a grammatical model on. [edit] Minimalism
  • 6. Main article: Minimalist program From the mid-1990s onwards, much research in transformational grammar has been inspired by Chomsky's Minimalist Program.[9] The "Minimalist Program" aims at the further development of ideas involving economy of derivation and economy of representation, which had started to become significant in the early 1990s, but were still rather peripheral aspects of Transformational-generative grammar theory. Economy of derivation is a principle stating that movements (i.e., transformations) only occur in order to match interpretable features with uninterpretable features. An example of an interpretable feature is the plural inflection on regular English nouns, e.g., dogs. The word dogs can only be used to refer to several dogs, not a single dog, and so this inflection contributes to meaning, making it interpretable. English verbs are inflected according to the number of their subject (e.g., "Dogs bite" vs "A dog bites"), but in most sentences this inflection just duplicates the information about number that the subject noun already has, and it is therefore uninterpretable. Economy of representation is the principle that grammatical structures must exist for a purpose, i.e., the structure of a sentence should be no larger or more complex than required to satisfy constraints on grammaticality. Both notions, as described here, are somewhat vague, and indeed the precise formulation of these principles is controversial.[10][11] An additional aspect of minimalist thought is the idea that the derivation of syntactic structures should be uniform; that is, rules should not be stipulated as applying at arbitrary points in a derivation, but instead apply throughout derivations. Minimalist approaches to phrase structure have resulted in "Bare Phrase Structure," an attempt to eliminate X-bar theory. In 1998, Chomsky suggested that derivations proceed in phases. The distinction of Deep Structure vs. Surface Structure is not present in Minimalist theories of syntax, and the most recent phase-based theories also eliminate LF and PF as unitary levels of representation. [edit] Mathematical representation Returning to the more general mathematical notion of a grammar, an important feature of all transformational grammars is that they are more powerful than context-free grammars.[12] This idea was formalized by Chomsky in the Chomsky hierarchy. Chomsky argued that it is impossible to describe the structure of natural languages using context-free grammars.[13] His general position regarding the non-context-freeness of natural language has held up since then, although his specific examples regarding the inadequacy of CFGs in terms of their weak generative capacity were later disproven.[14][15] [edit] Transformations The usual usage of the term 'transformation' in linguistics refers to a rule that takes an input typically called the Deep Structure (in the Standard Theory) or D-structure (in the extended standard theory or government and binding theory) and changes it in some restricted way to
  • 7. result in a Surface Structure (or S-structure). In TGG, Deep structures were generated by a set of phrase structure rules. For example, a typical transformation in TG is the operation of subject-auxiliary inversion (SAI). This rule takes as its input a declarative sentence with an auxiliary: "John has eaten all the heirloom tomatoes." and transforms it into "Has John eaten all the heirloom tomatoes?" In their original formulation (Chomsky 1957), these rules were stated as rules that held over strings of either terminals or constituent symbols or both. X NP AUX Y X AUX NP Y (where NP = Noun Phrase and AUX = Auxiliary) In the 1970s, by the time of the Extended Standard Theory, following the work of Joseph Emonds on structure preservation, transformations came to be viewed as holding over trees. By the end of government and binding theory in the late 1980s, transformations are no longer structure changing operations at all; instead they add information to already existing trees by copying constituents. The earliest conceptions of transformations were that they were construction-specific devices. For example, there was a transformation that turned active sentences into passive ones. A different transformation raised embedded subjects into main clause subject position in sentences such as "John seems to have gone"; and yet a third reordered arguments in the dative alternation. With the shift from rules to principles and constraints that was found in the 1970s, these construction-specific transformations morphed into general rules (all the examples just mentioned being instances of NP movement), which eventually changed into the single general rule of move alpha or Move. Transformations actually come of two types: (i) the post-Deep structure kind mentioned above, which are string or structure changing, and (ii) Generalized Transformations (GTs). Generalized transformations were originally proposed in the earliest forms of generative grammar (e.g., Chomsky 1957). They take small structures, either atomic or generated by other rules, and combine them. For example, the generalized transformation of embedding would take the kernel "Dave said X" and the kernel "Dan likes smoking" and combine them into "Dave said Dan likes smoking." GTs are thus structure building rather than structure changing. In the Extended Standard Theory and government and binding theory, GTs were abandoned in favor of recursive phrase structure rules. However, they are still present in tree-adjoining grammar as the Substitution and Adjunction operations, and they have recently re-emerged in mainstream generative grammar in Minimalism, as the operations Merge and Move. In generative phonology, another form of transformation is the phonological rule, which describes a mapping between an underlying representation (the phoneme) and the surface form that is articulated during natural speech.[16] [edit] See also
  • 8. Antisymmetry Generalised phrase structure grammar Generative semantics Head-driven phrase structure grammar Heavy NP shift Lexical functional grammar Parasitic gap [edit] References 1. ^ Chomsky, Noam (1995). The Minimalist Program. MIT Press. 2. ^ Chomsky, Noam (1965). Aspects of the Theory of Syntax. MIT Press. ISBN 0262530074. 3. ^ The Port-Royal Grammar of 1660 identified similar principles; Chomsky, Noam (1972). Language and Mind. Harcourt Brace Jovanovich. ISBN 0151478104. 4. ^ Jackendoff, Ray (1974). Semantic Interpretation in Generative Grammar. MIT Press. ISBN 0262100134. 5. ^ May, Robert C. (1977). The Grammar of Quantification. MIT Phd Dissertation. ISBN 0824013921. (Supervised by Noam Chomsky, this dissertation introduced the idea of "logical form.") 6. ^ Chomsky, Noam (1986). Knowledge of Language. New York:Praeger. ISBN 0275900258. 7. ^ Chomsky, Noam (2001). "Derivation by Phase." In other words, in algebraic terms, the I-Language is the actual function, whereas the E-Language is the extension of this function. In Michael Kenstowicz (ed.) Ken Hale: A Life in Language. MIT Press. Pages 1-52. (See p. 49 fn. 2 for comment on E-Language.) 8. ^ Newmeyer, Frederick J. (1986). Linguistic Theory in America (Second Edition). Academic Press. 9. ^ Chomsky, Noam (1995). The Minimalist Program. MIT Press. ISBN 0262531283. 10. ^ Lappin, Shalom; Robert Levine and David Johnson (2000). "Topic ... Comment". Natural Language & Linguistic Theory 18 (3): 665–671. doi:10.1023/A:1006474128258. 11. ^ Lappin, Shalom; Robert Levine and David Johnson (2001). "The Revolution Maximally Confused". Natural Language & Linguistic Theory 19 (4): 901–919. doi:10.1023/A:1013397516214. 12. ^ Peters, Stanley; R. Ritchie (1973). "On the generative power of transformational grammars". Information Sciences 6: 49–83. doi:10.1016/0020-0255(73)90027-3. 13. ^ Chomsky, Noam (1956). "Three models for the description of language". IRE Transactions on Information Theory 2 (3): 113–124. doi:10.1109/TIT.1956.1056813. 14. ^ Shieber, Stuart (1985). "Evidence against the context-freeness of natural language". Linguistics and Philosophy 8 (3): 333–343. doi:10.1007/BF00630917. 15. ^ Pullum, Geoffrey K.; Gerald Gazdar (1982). "Natural languages and context-free languages". Linguistics and Philosophy 4 (4): 471–504. doi:10.1007/BF00360802. 16. ^ Goldsmith, John A (1995). "Phonological Theory". In John A. Goldsmith. The Handbook of Phonological Theory. Blackwell Handbooks in Linguistics. Blackwell Publishers. p. 2. ISBN 1405157682.
  • 9. [edit] External links What is I-language? - Chapter 1 of I-language: An Introduction to Linguistics as Cognitive Science. The Syntax of Natural Language – an online textbook on transformational grammar. Part-of-speech tagging From Wikipedia, the free encyclopedia (Redirected from Part of speech tagger) In corpus linguistics, part-of-speech tagging (POS tagging or POST), also called grammatical tagging or word-category disambiguation, is the process of marking up the words in a text (corpus) as corresponding to a particular part of speech, based on both its definition, as well as its context —i.e. relationship with adjacent and related words in a phrase, sentence, or paragraph. A simplified form of this is commonly taught to school-age children, in the identification of words as nouns, verbs, adjectives, adverbs, etc. Once performed by hand, POS tagging is now done in the context of computational linguistics, using algorithms which associate discrete terms, as well as hidden parts of speech, in accordance with a set of descriptive tags. POS-tagging algorithms fall into two distinctive groups: rule-based and stochastic. E.Brill's tagger, one of the first and widely used English POS-taggers employs rule based algorithms. Contents [hide] 1 Principle 2 History o 2.1 The Brown Corpus o 2.2 Use of Hidden Markov Models o 2.3 Dynamic Programming methods o 2.4 Unsupervised taggers o 2.5 Other taggers and methods 3 Issues 4 See also 5 References 6 ^ STAR POS-tagger 7 External links [edit] Principle
  • 10. Part-of-speech tagging is harder than just having a list of words and their parts of speech, because some words can represent more than one part of speech at different times, and because some parts of speech are complex or unspoken. This is not rare—in natural languages (as opposed to many artificial languages), a large percentage of word-forms are ambiguous. For example, even "dogs", which is usually thought of as just a plural noun, can also be a verb: The sailor dogs the barmaid. Performing grammatical tagging will indicate that "dogs" is a verb, and not the more common plural noun, since one of the words must be the main verb, and the noun reading is less likely following "sailor" (sailor !→ dogs). Semantic analysis can then extrapolate that "sailor" and "barmaid" implicate "dogs" as 1) in the nautical context (sailor→<verb>←barmaid) and 2) an action applied to the object "barmaid" ([subject] dogs→barmaid). In this context, "dogs" is a nautical term meaning "fastens (a watertight barmaid) securely; applies a dog to". "Dogged", on the other hand, can be either an adjective or a past-tense verb. Just which parts of speech a word can represent varies greatly. Native speakers of a language perform grammatical and semantic analysis innately, and thus trained linguists can identify the grammatical parts of speech to various fine degrees depending on the tagging system. Schools commonly teach that there are 9 parts of speech in English: noun, verb, article, adjective, preposition, pronoun, adverb, conjunction, and interjection. However, there are clearly many more categories and sub-categories. For nouns, plural, possessive, and singular forms can be distinguished. In many languages words are also marked for their "case" (role as subject, object, etc.), grammatical gender, and so on; while verbs are marked for tense, aspect, and other things. In part-of-speech tagging by computer, it is typical to distinguish from 50 to 150 separate parts of speech for English, for example, NN for singular common nouns, NNS for plural common nouns, NP for singular proper nouns (see the POS tags used in the Brown Corpus). Work on stochastic methods for tagging Koine Greek (DeRose 1990) has used over 1,000 parts of speech, and found that about as many words were ambiguous there as in English. A morphosyntactic descriptor in the case of morphologically rich languages can be expressed like Ncmsan, which means Category=Noun, Type = common, Gender = masculine, Number = singular, Case = accusative, Animate = no. [edit] History [edit] The Brown Corpus Research on part-of-speech tagging has been closely tied to corpus linguistics. The first major corpus of English for computer analysis was the Brown Corpus developed at Brown University by Henry Kucera and Nelson Francis, in the mid-1960s. It consists of about 1,000,000 words of running English prose text, made up of 500 samples from randomly chosen publications. Each sample is 2,000 or more words (ending at the first sentence-end after 2,000 words, so that the corpus contains only complete sentences).
  • 11. The Brown Corpus was painstakingly "tagged" with part-of-speech markers over many years. A first approximation was done with a program by Greene and Rubin, which consisted of a huge handmade list of what categories could co-occur at all. For example, article then noun can occur, but article verb (arguably) cannot. The program got about 70% correct. Its results were repeatedly reviewed and corrected by hand, and later users sent in errata, so that by the late 70s the tagging was nearly perfect (allowing for some cases on which even human speakers might not agree). This corpus has been used for innumerable studies of word-frequency and of part-of-speech, and inspired the development of similar "tagged" corpora in many other languages. Statistics derived by analyzing it formed the basis for most later part-of-speech tagging systems, such as CLAWS (linguistics) and VOLSUNGA. However, by this time (2005) it has been superseded by larger corpora such as the 100 million word British National Corpus. For some time, part-of-speech tagging was considered an inseparable part of natural language processing, because there are certain cases where the correct part of speech cannot be decided without understanding the semantics or even the pragmatics of the context. This is extremely expensive, especially because analyzing the higher levels is much harder when multiple part-of- speech possibilities must be considered for each word. [edit] Use of Hidden Markov Models In the mid 1980s, researchers in Europe began to use hidden Markov models (HMMs) to disambiguate parts of speech, when working to tag the Lancaster-Oslo-Bergen Corpus of British English. HMMs involve counting cases (such as from the Brown Corpus), and making a table of the probabilities of certain sequences. For example, once you've seen an article such as 'the', perhaps the next word is a noun 40% of the time, an adjective 40%, and a number 20%. Knowing this, a program can decide that "can" in "the can" is far more likely to be a noun than a verb or a modal. The same method can of course be used to benefit from knowledge about following words. More advanced ("higher order") HMMs learn the probabilities not only of pairs, but triples or even larger sequences. So, for example, if you've just seen an article and a verb, the next item may be very likely a preposition, article, or noun, but much less likely another verb. When several ambiguous words occur together, the possibilities multiply. However, it is easy to enumerate every combination and to assign a relative probability to each one, by multiplying together the probabilities of each choice in turn. The combination with highest probability is then chosen. The European group developed CLAWS, a tagging program that did exactly this, and achieved accuracy in the 93-95% range. It is worth remembering, as Eugene Charniak points out in Statistical techniques for natural language parsing [1], that merely assigning the most common tag to each known word and the tag "proper noun" to all unknowns, will approach 90% accuracy because many words are unambiguous.
  • 12. CLAWS pioneered the field of HMM-based part of speech tagging, but was quite expensive since it enumerated all possibilities. It sometimes had to resort to backup methods when there were simply too many (the Brown Corpus contains a case with 17 ambiguous words in a row, and there are words such as "still" that can represent as many as 7 distinct parts of speech). HMMs underlie the functioning of stochastic taggers and are used in various algorithms one of the most widely used being the bi-directional inference algorithm [1]. [edit] Dynamic Programming methods In 1987, Steven DeRose and Ken Church independently developed dynamic programming algorithms to solve the same problem in vastly less time. Their methods were similar to the Viterbi algorithm known for some time in other fields. DeRose used a table of pairs, while Church used a table of triples and an ingenious method of estimating the values for triples that were rare or nonexistent in the Brown Corpus (actual measurement of triple probabilities would require a much larger corpus). Both methods achieved accuracy over 95%. DeRose's 1990 dissertation at Brown University included analyses of the specific error types, probabilities, and other related data, and replicated his work for Greek, where it proved similarly effective. These findings were surprisingly disruptive to the field of natural language processing. The accuracy reported was higher than the typical accuracy of very sophisticated algorithms that integrated part of speech choice with many higher levels of linguistic analysis: syntax, morphology, semantics, and so on. CLAWS, DeRose's and Church's methods did fail for some of the known cases where semantics is required, but those proved negligibly rare. This convinced many in the field that part-of-speech tagging could usefully be separated out from the other levels of processing; this in turn simplified the theory and practice of computerized language analysis, and encouraged researchers to find ways to separate out other pieces as well. Markov Models are now the standard method for part-of-speech assignment. [edit] Unsupervised taggers The methods already discussed involve working from a pre-existing corpus to learn tag probabilities. It is, however, also possible to bootstrap using "unsupervised" tagging. Unsupervised tagging techniques use an untagged corpus for their training data and produce the tagset by induction. That is, they observe patterns in word use, and derive part-of-speech categories themselves. For example, statistics readily reveal that "the", "a", and "an" occur in similar contexts, while "eat" occurs in very different ones. With sufficient iteration, similarity classes of words emerge that are remarkably similar to those human linguists would expect; and the differences themselves sometimes suggest valuable new insights.[citation needed] These two categories can be further subdivided into rule-based, stochastic, and neural approaches.
  • 13. [edit] Other taggers and methods Some current major algorithms for part-of-speech tagging include the Viterbi algorithm, Brill Tagger, Constraint Grammar, and the Baum-Welch algorithm (also known as the forward- backward algorithm). Hidden Markov model and visible Markov model taggers can both be implemented using the Viterbi algorithm. Many machine learning methods have also been applied to the problem of POS tagging. Methods such as SVM, Maximum entropy classifier, Perceptron, and Nearest-neighbor have all been tried, and most can achieve accuracy above 95%. A direct comparison of several methods is reported (with references) at [2]. This comparison uses the Penn tag set on some of the Penn Treebank data, so the results are directly comparable. However, many significant taggers are not included (perhaps because of the labor involved in reconfiguring them for this particular dataset). Thus, it should not be assumed that the results reported there are the best that can be achieved with a given approach; nor even the best that have been achieved with a given approach. [edit] Issues While there is broad agreement about basic categories, a number of edge cases make it difficult to settle on a single "correct" set of tags, even in a single language such as English. For example, it is hard to say whether "fire" is functioning as an adjective or a noun in the big green fire truck A second important example is the use/mention distinction, as in the following example, where "blue" is clearly not functioning as an adjective (the Brown Corpus tag set appends the suffix "- NC" in such cases): the word "blue" has 4 letters. Words in a language other than that of the "main" text, are commonly tagged as "foreign", usually in addition to a tag for the role the foreign word is actually playing in context. There are also many cases where POS categories and "words" do not map one to one, for example: David's gonna don't vice versa first-cut cannot pre- and post-secondary look (a word) up
  • 14. In the last example, "look" and "up" arguably function as a single verbal unit, despite the possibility of other words coming between them. Some tag sets (such as Penn) break hyphenated words, contractions, and possessives into separate tokens, thus avoiding some but far from all such problems. It is unclear whether it is best to treat words such as "be", "have", and "do" as categories in their own right (as in the Brown Corpus), or as simply verbs (as in the LOB Corpus and the Penn Treebank). "be" has more forms than other English verbs, and occurs in quite different grammatical contexts, complicating the issue. The most popular "tag set" for POS tagging for American English is probably the Penn tag set, developed in the Penn Treebank project. It is largely similar to the earlier Brown Corpus and LOB Corpus tag sets, though much smaller. In Europe, tag sets from the Eagles Guidelines see wide use, and include versions for multiple languages. POS tagging work has been done in a variety of languages, and the set of POS tags used varies greatly with language. Tags usually are designed to include overt morphological distinctions (this makes the tag sets for heavily inflected languages such as Greek and Latin very large; and makes tagging words in agglutinative languages such an Inuit virtually impossible. However, Petrov, D. Das, and R. McDonald ("A Universal Part-of-Speech Tagset" http://arxiv.org/abs/1104.2086) have proposed a "universal" tag set, with 12 categories (for example, no subtypes of nouns, verbs, punctuation, etc; no distinction of "to" as an infinitive marker vs. preposition, etc). Whether a very small set of very broad tags, or a much larger set of more precise ones, is preferable, depends on the purpose at hand. Automatic tagging is easier on smaller tag-sets. [edit] See also Semantic net Sliding window based part-of-speech tagging Trigram tagger Word sense disambiguation [edit] References Charniak, Eugene. 1997. "Statistical Techniques for Natural Language Parsing". AI Magazine 18(4):33–44. Hans van Halteren, Jakub Zavrel, Walter Daelemans. 2001. Improving Accuracy in NLP Through Combination of Machine Learning Systems. Computational Linguistics. 27(2): 199–229. PDF DeRose, Steven J. 1990. "Stochastic Methods for Resolution of Grammatical Category Ambiguity in Inflected and Uninflected Languages." Ph.D. Dissertation. Providence, RI: Brown University Department of Cognitive and Linguistic Sciences. DeRose, Steven J. 1988. "Grammatical category disambiguation by statistical optimization." Computational Linguistics 14(1): 31–39. [3]
  • 15. [edit] 1. ^ STAR POS-tagger [edit] External links Overview of available taggers Cypher A natural language transcoder that performs POS-tagging, morphological processing, lexical analysis, to produce RDF and SPARQL from natural language BROKEN LINK Resources for Studying English Syntax Online CLAWS LingPipe Commercial Java natural language processing software including trainable part-of- speech taggers with first-best, n-best and per-tag confidence output. OpenNLP Tagger AL 2.0 Tagger based on maxent and perceptron classifiers CRFTagger Conditional Random Fields (CRFs) English POS Tagger JTextPro A Java-based Text Processing Toolkit Citar LGPL C++ Hidden Markov Model trigram POS tagger, a Java port named Jitar is also available Ninja-PoST PHP port of GPoSTTL, based on Eric Brill's rule-based tagger ComplexityIntelligence, LLC Free and Commercial NLP Web Services for Part Of Speech Tagging (and Named Entity Recognition) Part-of-Speech tagging based on Soundex features FastTag - LGPL Java POS tagger based on Eric Brill's rule-based tagger jspos - LGPL Javascript port of FastTag Topia TermExtractor - Python implementation of the UPenn BioIE parts-of-speech algorithm