3. Presentation
Schedule:
http://faculty.washington.edu/melihay/MEBI591C.htm
50 minutes presentation+discussion+question answering
Content:
Research/Project Idea
Motivation + Problem + Potential Solution
Survey or literature review
A general area
Text mining: named entity recognition - gene name identification
Data Mining: classification, clustering
Available resources for a given area
Open source libraries
Data resources
Paper
Conference or journal article
Preparation:
Email the plan + reading list at least 3 days prior to class
GoMap Discussion List
4. System Design
Team:
Marcin, Wynona, Karl, Stella, Francisco, Jeffry, Safiyyah
(not registered)
Example data released:
https://www.i2b2.org/NLP/Relations/Documentation.php
The fourth i2b2 challenge is a three tiered challenge
that studies:
1. extraction of medical problems, tests, and treatments
2. classification of assertions made on medical problems
3. relations of medical problems, tests, and treatments
5. 2010 - I2b2 Challenge
Important Dates:
March 5th – Registration opens
April 15th – Commitment to Participate in Challenge &
Training Data Release
July 15th – Test Data Release
September 1st – Short papers due
October 1st – Invitations to present at the Workshop
November, 2010 – Workshop
Preparations
Linux server + accounts (meliha)
Accounts
Dev environment
Subversion ?
7. Sentence Delimiters
Document -> Paragraph -> Sentences
Sentence boundary disambiguation (SBD) is the problem in
NLP of deciding where sentences begin and end.
Sentence boundary identification is challenging because
punctuation marks are often ambiguous.
period may denote
Abbreviation
Decimal point
Email address
About 47% of the periods in the Wall Street Journal corpus denote
abbreviations.
Question marks and exclamation marks may appear
embedded quotations, emotions, computer code, and slang
Tools:
OpenNLP has a class for sentence detection
NacTEM: http://text0.mib.man.ac.uk:8080/scottpiao/sent_detector
8. Tokenization
Document -> Paragraph -> Sentence -> Tokens
Based on white-space characters
In Unicode (Unicode Character Database) the following
codepoints are defined as whitespace:
U+0009–U+000D (control characters, containing Tab, CR and LF)
U+0020 SPACE
U+0085 NEL (control character next line)
U+00A0 NBSP (NO-BREAK SPACE)
U+1680 OGHAM SPACE MARK
U+180E MONGOLIAN VOWEL SEPARATOR
U+2000–U+200A (different sorts of spaces)
U+2028 LS (LINE SEPARATOR)
U+2029 PS (PARAGRAPH SEPARATOR)
U+202F NNBSP (NARROW NO-BREAK SPACE)
U+205F MMSP (MEDIUM MATHEMATICAL SPACE)
U+3000 IDEOGRAPHIC SPACE
9. Part-OF-Speech Tagging
“The process of assigning a part-of-speech or
other lexical class marker to each word in a
corpus” (Jurafsky and Martin)
WORDS
TAGS
the
girl
kissed N
the V
boy P
on DET
the
cheek
10. Penn Tree POS Tags
1. CC Coordinating conjunction 19. PRP$ Possessive pronoun
2. CD Cardinal number 20. RB Adverb
3. DT Determiner 21. RBR Adverb, comparative
4. EX Existential there 22. RBS Adverb, superlative
5. FW Foreign word 23. RP Particle
6. IN Preposition or subordinating conjunction 24. SYM Symbol
7. JJ Adjective 25. TO to
8. JJR Adjective, comparative 26. UH Interjection
9. JJS Adjective, superlative 27. VB Verb, base form
10. LS List item marker 28. VBD Verb, past tense
11. MD Modal 29. VBG Verb, gerund or present participle
12. NN Noun, singular or mass 30. VBN Verb, past participle
13. NNS Noun, plural 31. VBP Verb, non-3rd person singular present
14. NNP Proper noun, singular 32. VBZ Verb, 3rd person singular present
15. NNPS Proper noun, plural 33. WDT Wh-determiner
16. PDT Predeterminer 34. WP Wh-pronoun
17. POS Possessive ending 35. WP$ Possessive wh-pronoun
18. PRP Personal pronoun 36. WRB Wh-adverb
11. Applications of Tagging
Partial parsing: syntactic analysis
Information Extraction: tagging and partial parsing help
identify useful terms and relationships between them.
Information Retrieval: noun phrase recognition and
query-document matching based on meaningful units
rather than individual terms.
Question Answering: analyzing a query to understand
what type of entity the user is looking for and how it is
related to other noun phrases mentioned in the question.
12. Information Souces in Tagging
How do we decide the correct POS for a word?
Syntagmatic Information: Look at tags of other words in
the context of the word we are interested in.
Lexical Information: Predicting a tag based on the word
concerned. For words with a number of POS, they usually
occur used as one particular POS.
13. POS Approaches – Rule Bases
• Basic Idea:
– Assign all possible tags to words
– Remove tags according to set of rules of type: if word+1 is an
adj, adv, or quantifier and the following is a sentence boundary
and word-1 is not a verb like “consider” then eliminate non-adv
else eliminate adv.
– Typically more than 1000 hand-written rules, but may be
machine-learned.
14. POS Approaches – Machine Learning
• Based on probability of certain tag occurring given
various possibilities
• Requires a training corpus
• Training corpus may be different from test corpus.
• Examples
• Hidden Markov Model Taggers
• Transformation Based Taggers
• Maximum Entropy Taggers
Ling572 (Advanced Statistical Methods in NLP) -
http://courses.washington.edu/ling572/winter10/teaching_slides/ne
w_syllabus.htm
15. Tagging Accuracy
Ranges from 95%-97%
Depends on:
Amount of training data available.
Difference between training corpus and dictionary and
the corpus of application.
Unknown words in the corpus of application.
16. Tagging Unknown Words
• New words added to (newspaper) language 20+ per
month
• Plus many proper names …
• Increases error rates by 1-2%
• Method 1: assume they are nouns
• Method 2: assume the unknown words have a
probability distribution similar to words only occurring
once in the training set.
• Method 3: Use morphological information, e.g., words
ending with –ed tend to be tagged VBN.
17. POS Taggers
Freely downloadable Part of Speech Taggers
Stanford POS taggerLoglinear tagger in Java (by Kristina Toutanova)
hunpos An HMM tagger with models available for English and Hungarian. A reimplementation of
TnT (see below) in OCaml. pre-compiled models. Runs on Linux, Mac OS X, and Windows.
MBT: Memory-based Tagger Based on TiMBLTreeTagger A decision tree based tagger from the
University of Stuttgart (Helmut Scmid). It's language independent, but comes complete with
parameter files for English, German, Italian, Dutch, French, Old French, Spanish, Bulgarian, and
Russian. (Linux, Sparc-Solaris, Windows, and Mac OS X versions. Binary distribution only.) Page
has links to sites where you can run it online.
SVMTool POS Tagger based on SVMs (uses SVMlight). LGPL.
ACOPOST (formerly ICOPOST) Open source C taggers originally written by by Ingo Schröder.
Implements maximum entropy, HMM trigram, and transformation-based learning. C source
available under GNU public license.
MXPOST: AdwaitRatnaparkhi's Maximum Entropy part of speech tagger Java POS tagger. A
sentence boundary detector (MXTERMINATOR) is also included. Original version was only
JDK1.1; later version worked with JDK1.3+. Class files, not source.
fnTBL A fast and flexible implementation of Transformation-Based Learning in C++. Includes a
POS tagger, but also NP chunking and general chunking models.
mu-TBL An implementation of a Transformation-based Learner (a la Brill), usable for POS tagging
and other things by Torbjörn Lager. Web demo also available. Prolog.
YamCha SVM-based NP-chunker, also usable for POS tagging, NER, etc. C/C++ open source.
Won CoNLL 2000 shared task. (Less automatic than a specialized POS tagger for an end user.)
QTAG Part of speech tagger An HMM-based Java POS tagger from Birmingham U. (Oliver
Mason). English and German parameter files. [Java class files, not source.]
18. Collocations
A collocation is an expression consisting two or more
words that correspond to some conventional way of
saying things
Methods:
Simplest solution – counting
Google 5-gram corpus (2006)
ceramics collectables fine 130
ceramics collected by 52
ceramics collection , 144
ceramics collection . 247
Use POS Tags
Use Noun Phrase Chunking / Parsing
19. NLP/Text Mining POINTERS
NLP BOOKS:
Manning and Schütze, Foundations of Statistical Natural
Language Processing (MIT Press, 1999).
Jurafsky, Daniel, and James H. Martin. 2009. Speech and
Language Processing: An Introduction to Natural
Language Processing, Speech Recognition, and
Computational Linguistics. 2nd edition. Prentice-Hall.
20. Books on Regular Expressions
Jeffrey E.F. Friedl, Mastering Regular Expressions,
O’Reilly.
Jan Goyvaerts, Regular Expressions Cookbook,
O’Reilly
21. NLP Research Groups
Stanford NLP Group
http://nlp.stanford.edu/
CMU NLP Group
http://www.cs.cmu.edu/~nasmith/nlp-cl.html
Upenn NLP Group
http://nlp.cis.upenn.edu/
NACTEM – National Center for Text Mining
http://www.nactem.ac.uk/
UW – Turing Center
http://turing.cs.washington.edu/
22. NLP Libraries
List of tools from Stanford NLP webpage
http://nlp.stanford.edu/links/statnlp.html
Mallet – Machine learning for language toolkit
MALLET is a Java-based package for statistical natural language
processing, document classification, clustering, topic modeling, information
extraction, and other machine learning applications to text.
UMASS - http://mallet.cs.umass.edu/
Minorthird
MinorThird is a collection of Java classes for storing text, annotating text, and
learning to extract entities and categorize text.
CMU - http://sourceforge.net/apps/trac/minorthird/wiki
OpenNLP
OpenNLP hosts a variety of java-based NLP tools which perform sentence
detection, tokenization, pos-tagging, chunking and parsing, named-entity
detection, and coreference using the OpenNLPMaxent machine learning package.
http://opennlp.sourceforge.net/
GATE
General architecture for NLP tasks
http://gate.ac.uk/
23. Biomedical NLP and Text Mining Tools
Metamap (MMTx) - NLM
http://mmtx.nlm.nih.gov/
Negex, Context – University of Pittsburg – BluLab
http://www.dbmi.pitt.edu/blulab/index.html
Ctakes – Mayo Clinic
https://cabig-
kc.nci.nih.gov/Vocab/KC/index.php/OHNLP_Documentati
on_and_Downloads
24. Bio-medicial Text Mining Tools
Chilibot — A tool for finding relationships between genes or gene products.
EBIMed - EBIMed is a web application that combines Information Retrieval and Extraction from Medline. [1]
FABLE — A gene-centric text-mining search engine for Medline
GOAnnotator, an online tool that uses semantic similarity for verification of electronic protein annotations using GO
terms automatically extracted from literature.
GoPubMed — retrieves Medline abstracts for your search query, then detects ontology terms from the Gene
Ontology and Medical Subject Headings in the abstracts and allows the user to browse the search results by
exploring the ontologies and displaying only papers mentioning selected terms, their synonyms or descendants.
Information Hyperlinked Over Proteins (iHOP)[2]: "A network of concurring genes and proteins extends through the
scientific literature touching on phenotypes, pathologies and gene function. iHOP provides this network as a natural
way of accessing millions of Medline abstracts. By using genes and proteins as hyperlinks between sentences and
abstracts, the information in Medline can be converted into one navigable resource, bringing all advantages of the
internet to scientific literature research."
LitInspector — Gene and signal transduction pathway data mining in Medline abstracts.
NextBio- Life sciences search engine with a text mining functionality that utilizes Medline abstracts and clinical trials
to return concepts relevant to the query based on a number of heuristics including ontology relationships, journal
impact, publication date, and authorship.
PubAnatomy — An interactive visual search engine that provides new ways to explore relationships among Medline
literature, text mining results, anatomical structures, gene expression and other background information.
PubGene — Co-occurrence network display of gene and protein symbols as well as MeSH, GO, PubChem and
interaction terms (such as "binds" or "induces") as these appear in Medline records (that is, PubMed titles and
abstracts).
TexFlame, an online tool that renders a single Medline abstract as a Systems Biology Graphical Notation (SBGN)-
like graph. The graph is a complete syntactic-semantic representation of the abstract.
Whatizit - Whatizit is great at identifying molecular biology terms and linking them to publicly available databases.
XTractor — Discovering Newer Scientific Relations Across PubMed Abstracts. A tool to obtain manually
annotated,expertcurated relationships for Proteins, Diseases, Drugs and Biological Processes as they get
published in Medline.
25. Literature-based discovery tools
Arrowsmith - UIC-based site for searching links
between two literatures within Medline. Also contains
the Author-ity tool for disambiguating authors on
scientific papers, and the Anne O'Tate tool for
summarizing a results of a PubMed query.
BITOLAhelps biomedical researchers make new
discoveries by discovering potentially new relations
between biomedical concepts.
Manjal another LBD tools by PadminiSrinivasan
Editor's Notes
People who haven’t returned me with dates: Daniel and Marcin
Stanford: Chris Manning and DanielJurafskyCMU: William Cohen