Templates in linguistics - Why Garbage Garbage

Templates in Linguistics: Why
Garbage Garbage?
Presented by:
Hussein Ghaly
1- Garbage Disposal
Yaseen Ghaly, 3 Years Old:
• Papy laih zebala zebala? (Dad, why
garbage garbage?) > Why are you
carrying two garbage bags?
• Papy laih bang bang? (Dad, why bang
bang?) > Why are you making this “bang
bang/hammering” sound?
2- Making a Template
• Yaseen seems to be using this template:
• “Papy, laih X?” (Dad, why X)
• Where X can be anything:
– Garbage Garbage
– Bang Bang
– Sleeping
– …
– 天空是绿色的 (foreign word/code switching)
3- To build a language
• How can the linguistic expression from
simple sentences into language such as
ours?
• Answer: Recursion
4- Recursively
• An example of
recursion found
by Salma Ghaly,
6 Years old.
Main Claim
• Language is built using simple (idiomatic)
templates. The complexity comes from
recursion.
Outline
• Starting Assumptions
• Learning templates (Language Acquisition)
• Cross Linguistic Template Linearity
• Selecting A template (Semantic-Pragmatic
Prompt)
• Extending A template (Template Malleability)
• Applications of Templates (Information
Extraction and Machine Translation)
Starting Assumptions - Syntax
• In the syntax literature, language is a
lexicon of words, and a computational
system to put these words where they
should form a grammatical sentence.
Lexicon
Computation
System
Starting Assumptions – Templates
Framework
• The “lexicon”, which is stored in the memory, is extended
with a list of templates, also stored in memory.
• The computational system only manages what to fill the
placeholders within templates.
Word Lexicon Computation
System
Template Lexicon
Learning Templates
• The “garbage gabage” example indicates:
– A child can intuitively form a template for
plurals (that is applicable in some human
languages such as Bhasa Malaysia (e.g.
kanak kanak=children)
– A child can put anything in the placeholder X
within the sentence template “Dad, Why X?”
• But these hypotheses would need further
evidence from First Language Acquistion
Template Linearity
• English
– I love you.
– I miss you.
– I need you.
• French
– Je t’aime.
– Tu me manques.
– J’ai besoin de toi.
Clearly, the linear order is very different between Constructions in
different languages.
This should entice us to think about how these constructions are
generated.
Semantic-Pragmatic Prompt
• An area of overlap between the reason, context,
and information content of some sentence.
• Start with list of arguments (X1: I, X2: You)
• I Want to express [+feeling] [+positive]
[+distance], therefore:
– in English, we invoke the template I miss X2.
– In French, we invoke the template X2 me manques
(with some adjustments depending on pronouns, etc)
• So I can utter the sentence after filling the
template:
– I miss Randa.
– Randa me manque.
Template Variability
• Almost everything can be said in an alternative
way:
– Godzilla destroyed the City, which is unfortunate.
– It is unfortunate that Godzilla destroyed the city.
– The destruction of the city by Godzilla is unfortunate.
• So, there are different templates to express the
relation between these four entities (being
unfortunate, the destruction, Godzilla, the City).
This again feeds into the argument of non-
linearity of templates, this time within the same
language.
Template Malleability
• Meaning how easy the template can be re-
shaped. This includes the following:
– Tense malleability:
• John was eating fish.
• John has been eating fish.
– Synonym malleability:
• Sarah cannot tolerate this any more.
• Sarah cannot put up with this anymore.
• The idea of malleability enables us to avoid
accounting for hundreds of millions of
combinations of basic templates.
Using Templates
• For information Extraction (e.g. Banko and
Etzioni 2008), where templates where
used to extract (is-a) relationships
between entities.
Using Templates in Machine
Translation
• Was first suggested by (Nagao, 1984)
under the name of Example-Based
Machine Translation. He also indicted this
approach is relevant to Second Language
Acquisition.
Using Templates in Machine
Translation
• Current state of the
art Phrase-Based
Statistical Machine
Translation
techniques uses
contiguous chunks.
(Koehn, 2010)
Using Templates in Machine
Translation
• But using contiguous chunks misses many
phrases where there is a difference in
word order between the two languages.
- needs a lot of training data 
• To compensate for this, a statistical
reordering model is used
- can make the output unintelligible 
Using Templates in Machine
Translation
Chunk:
Michael assumes that he will stay in the house ->
Michael geht davon aus, dass er im haus bleibt
Subchunks:
Michael -> Michael
in the house -> im haus
So by removing (stenciling) subcunks from the chunk we get a translation template
X1 assumes that he will stay X2 ->
X1 geht davon aus, dass er X2 bleibt
- preserves word order 
- can apply to many sentences not seen before 
- requires less training data 
- can set restrictions on the type of placeholders (X1: NP , X2: PP) 
•Thank X1!
(X1 = You )
1 of 20

Recommended

Moses Statistical Machine Translation tool by
Moses Statistical Machine Translation toolMoses Statistical Machine Translation tool
Moses Statistical Machine Translation toolyashothara shanmugarajah
212 views42 slides
Lexicology Ii Wordformation by
Lexicology Ii   WordformationLexicology Ii   Wordformation
Lexicology Ii Wordformationacostaena
9.1K views25 slides
Alp Öktem - 2017 - Automatic Extraction of Parallel Speech Corpora from Dubbe... by
Alp Öktem - 2017 - Automatic Extraction of Parallel Speech Corpora from Dubbe...Alp Öktem - 2017 - Automatic Extraction of Parallel Speech Corpora from Dubbe...
Alp Öktem - 2017 - Automatic Extraction of Parallel Speech Corpora from Dubbe...Association for Computational Linguistics
147 views20 slides
Processes of word formation by
Processes of word formationProcesses of word formation
Processes of word formationfurrakhabbas
184.9K views19 slides
Biblioteca by
BibliotecaBiblioteca
BibliotecaMartina y Aiora
452 views6 slides
Burn The Fat by
Burn The FatBurn The Fat
Burn The Fatomamuminogho zeal
130 views1 slide

More Related Content

Viewers also liked

Salida al MAS by
Salida al MASSalida al MAS
Salida al MASMartina y Aiora
394 views10 slides
Berns, Clancy & Assoc - 1997 by
Berns, Clancy & Assoc - 1997Berns, Clancy & Assoc - 1997
Berns, Clancy & Assoc - 1997Kelly Lock
95 views1 slide
цветы by
цветыцветы
цветыОлеся Кузьо
187 views4 slides
Cursodeverano ddhh ai_malaga by
Cursodeverano ddhh ai_malagaCursodeverano ddhh ai_malaga
Cursodeverano ddhh ai_malagaRuth Ainhoa De Frutos García
157 views2 slides
Partons en voyage humanitaire avec oeeo. by
Partons en voyage humanitaire avec oeeo.Partons en voyage humanitaire avec oeeo.
Partons en voyage humanitaire avec oeeo.Réseau Pro Santé
238 views1 slide
Segundactividalber by
SegundactividalberSegundactividalber
SegundactividalberAlbert Damian
199 views13 slides

Similar to Templates in linguistics - Why Garbage Garbage

Data collection and Materials Development by
Data collection and Materials DevelopmentData collection and Materials Development
Data collection and Materials DevelopmentRabby Zibon
2K views37 slides
Deep network notes.pdf by
Deep network notes.pdfDeep network notes.pdf
Deep network notes.pdfRamya Nellutla
6 views54 slides
9 -en- assessment feedback - political writing by
9 -en- assessment feedback - political writing9 -en- assessment feedback - political writing
9 -en- assessment feedback - political writingLuke Brewer
292 views38 slides
Optional Phonics Review Webinar July 6 by
Optional Phonics Review Webinar July 6Optional Phonics Review Webinar July 6
Optional Phonics Review Webinar July 6Peggy Semingson
534 views28 slides
Linguascope2018 by
Linguascope2018Linguascope2018
Linguascope2018Isabelle Jones
4.9K views59 slides
FinalReport by
FinalReportFinalReport
FinalReportVinh Xuan Ho
138 views4 slides

Similar to Templates in linguistics - Why Garbage Garbage(20)

Data collection and Materials Development by Rabby Zibon
Data collection and Materials DevelopmentData collection and Materials Development
Data collection and Materials Development
Rabby Zibon2K views
9 -en- assessment feedback - political writing by Luke Brewer
9 -en- assessment feedback - political writing9 -en- assessment feedback - political writing
9 -en- assessment feedback - political writing
Luke Brewer292 views
Optional Phonics Review Webinar July 6 by Peggy Semingson
Optional Phonics Review Webinar July 6Optional Phonics Review Webinar July 6
Optional Phonics Review Webinar July 6
Peggy Semingson534 views
5810 day 3 sept 20 2014 by SVTaylor123
5810 day 3 sept 20 2014 5810 day 3 sept 20 2014
5810 day 3 sept 20 2014
SVTaylor123426 views
Comparative study of Text-to-Speech Synthesis for Indian Languages by using S... by ravi sharma
Comparative study of Text-to-Speech Synthesis for Indian Languages by using S...Comparative study of Text-to-Speech Synthesis for Indian Languages by using S...
Comparative study of Text-to-Speech Synthesis for Indian Languages by using S...
ravi sharma218 views
Power point presentation course 1 by Jamileth Bedoya
Power point presentation course 1Power point presentation course 1
Power point presentation course 1
Jamileth Bedoya3.4K views
MFL tools and tricks - update Dec14 by jonmeier
MFL tools and tricks - update Dec14MFL tools and tricks - update Dec14
MFL tools and tricks - update Dec14
jonmeier1.1K views
B.tech i ecls_u-2_framing sentences and vocabulary by Rai University
B.tech i ecls_u-2_framing sentences and vocabularyB.tech i ecls_u-2_framing sentences and vocabulary
B.tech i ecls_u-2_framing sentences and vocabulary
Rai University1.6K views
Use Discourse to Access Language and Mathematics for English Learners by DreamBox Learning
Use Discourse to Access Language and Mathematics for English LearnersUse Discourse to Access Language and Mathematics for English Learners
Use Discourse to Access Language and Mathematics for English Learners
DreamBox Learning1.1K views
Jayakumar sentence pattern method-a new approach for teaching spoken english ... by Jayakumar K S
Jayakumar sentence pattern method-a new approach for teaching spoken english ...Jayakumar sentence pattern method-a new approach for teaching spoken english ...
Jayakumar sentence pattern method-a new approach for teaching spoken english ...
Jayakumar K S1.5K views
B.sc i ecls_u-2_framing sentences and vocabulary by Rai University
B.sc i ecls_u-2_framing sentences and vocabularyB.sc i ecls_u-2_framing sentences and vocabulary
B.sc i ecls_u-2_framing sentences and vocabulary
Rai University1.5K views
5810 day 3 sept 20 2014 by SVTaylor123
5810 day 3 sept 20 2014 5810 day 3 sept 20 2014
5810 day 3 sept 20 2014
SVTaylor123414 views
Bjmc i ecls_u-2_framing sentences and vocabulary by Rai University
Bjmc i ecls_u-2_framing sentences and vocabularyBjmc i ecls_u-2_framing sentences and vocabulary
Bjmc i ecls_u-2_framing sentences and vocabulary
Rai University528 views
Diploma i ecls_u-2_framing sentences and vocabulary by Rai University
Diploma i ecls_u-2_framing sentences and vocabularyDiploma i ecls_u-2_framing sentences and vocabulary
Diploma i ecls_u-2_framing sentences and vocabulary
Rai University1.1K views
Bdft i ecls_u-2_framing sentences and vocabulary by Rai University
Bdft i ecls_u-2_framing sentences and vocabularyBdft i ecls_u-2_framing sentences and vocabulary
Bdft i ecls_u-2_framing sentences and vocabulary
Rai University238 views
Bdft i ecls_u-2_framing sentences and vocabulary by Rai University
Bdft i ecls_u-2_framing sentences and vocabularyBdft i ecls_u-2_framing sentences and vocabulary
Bdft i ecls_u-2_framing sentences and vocabulary
Rai University463 views
Bba i ecls_u-2_framing sentences and vocabulary by Rai University
Bba i ecls_u-2_framing sentences and vocabularyBba i ecls_u-2_framing sentences and vocabulary
Bba i ecls_u-2_framing sentences and vocabulary
Rai University1.2K views

Recently uploaded

ICS3211_lecture 08_2023.pdf by
ICS3211_lecture 08_2023.pdfICS3211_lecture 08_2023.pdf
ICS3211_lecture 08_2023.pdfVanessa Camilleri
187 views30 slides
On Killing a Tree.pptx by
On Killing a Tree.pptxOn Killing a Tree.pptx
On Killing a Tree.pptxAncyTEnglish
66 views11 slides
Computer Introduction-Lecture06 by
Computer Introduction-Lecture06Computer Introduction-Lecture06
Computer Introduction-Lecture06Dr. Mazin Mohamed alkathiri
102 views12 slides
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdf by
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdfCWP_23995_2013_17_11_2023_FINAL_ORDER.pdf
CWP_23995_2013_17_11_2023_FINAL_ORDER.pdfSukhwinderSingh895865
536 views6 slides
Use of Probiotics in Aquaculture.pptx by
Use of Probiotics in Aquaculture.pptxUse of Probiotics in Aquaculture.pptx
Use of Probiotics in Aquaculture.pptxAKSHAY MANDAL
104 views15 slides
Create a Structure in VBNet.pptx by
Create a Structure in VBNet.pptxCreate a Structure in VBNet.pptx
Create a Structure in VBNet.pptxBreach_P
75 views8 slides

Recently uploaded(20)

Use of Probiotics in Aquaculture.pptx by AKSHAY MANDAL
Use of Probiotics in Aquaculture.pptxUse of Probiotics in Aquaculture.pptx
Use of Probiotics in Aquaculture.pptx
AKSHAY MANDAL104 views
Create a Structure in VBNet.pptx by Breach_P
Create a Structure in VBNet.pptxCreate a Structure in VBNet.pptx
Create a Structure in VBNet.pptx
Breach_P75 views
CUNY IT Picciano.pptx by apicciano
CUNY IT Picciano.pptxCUNY IT Picciano.pptx
CUNY IT Picciano.pptx
apicciano54 views
Ch. 7 Political Participation and Elections.pptx by Rommel Regala
Ch. 7 Political Participation and Elections.pptxCh. 7 Political Participation and Elections.pptx
Ch. 7 Political Participation and Elections.pptx
Rommel Regala105 views
The Accursed House by Émile Gaboriau by DivyaSheta
The Accursed House  by Émile GaboriauThe Accursed House  by Émile Gaboriau
The Accursed House by Émile Gaboriau
DivyaSheta212 views
AUDIENCE - BANDURA.pptx by iammrhaywood
AUDIENCE - BANDURA.pptxAUDIENCE - BANDURA.pptx
AUDIENCE - BANDURA.pptx
iammrhaywood89 views
Narration lesson plan by TARIQ KHAN
Narration lesson planNarration lesson plan
Narration lesson plan
TARIQ KHAN59 views
Psychology KS4 by WestHatch
Psychology KS4Psychology KS4
Psychology KS4
WestHatch90 views
REPRESENTATION - GAUNTLET.pptx by iammrhaywood
REPRESENTATION - GAUNTLET.pptxREPRESENTATION - GAUNTLET.pptx
REPRESENTATION - GAUNTLET.pptx
iammrhaywood107 views
11.30.23 Poverty and Inequality in America.pptx by mary850239
11.30.23 Poverty and Inequality in America.pptx11.30.23 Poverty and Inequality in America.pptx
11.30.23 Poverty and Inequality in America.pptx
mary850239167 views
Classification of crude drugs.pptx by GayatriPatra14
Classification of crude drugs.pptxClassification of crude drugs.pptx
Classification of crude drugs.pptx
GayatriPatra1492 views
Monthly Information Session for MV Asterix (November) by Esquimalt MFRC
Monthly Information Session for MV Asterix (November)Monthly Information Session for MV Asterix (November)
Monthly Information Session for MV Asterix (November)
Esquimalt MFRC58 views

Templates in linguistics - Why Garbage Garbage

  • 1. Templates in Linguistics: Why Garbage Garbage? Presented by: Hussein Ghaly
  • 2. 1- Garbage Disposal Yaseen Ghaly, 3 Years Old: • Papy laih zebala zebala? (Dad, why garbage garbage?) > Why are you carrying two garbage bags? • Papy laih bang bang? (Dad, why bang bang?) > Why are you making this “bang bang/hammering” sound?
  • 3. 2- Making a Template • Yaseen seems to be using this template: • “Papy, laih X?” (Dad, why X) • Where X can be anything: – Garbage Garbage – Bang Bang – Sleeping – … – 天空是绿色的 (foreign word/code switching)
  • 4. 3- To build a language • How can the linguistic expression from simple sentences into language such as ours? • Answer: Recursion
  • 5. 4- Recursively • An example of recursion found by Salma Ghaly, 6 Years old.
  • 6. Main Claim • Language is built using simple (idiomatic) templates. The complexity comes from recursion.
  • 7. Outline • Starting Assumptions • Learning templates (Language Acquisition) • Cross Linguistic Template Linearity • Selecting A template (Semantic-Pragmatic Prompt) • Extending A template (Template Malleability) • Applications of Templates (Information Extraction and Machine Translation)
  • 8. Starting Assumptions - Syntax • In the syntax literature, language is a lexicon of words, and a computational system to put these words where they should form a grammatical sentence. Lexicon Computation System
  • 9. Starting Assumptions – Templates Framework • The “lexicon”, which is stored in the memory, is extended with a list of templates, also stored in memory. • The computational system only manages what to fill the placeholders within templates. Word Lexicon Computation System Template Lexicon
  • 10. Learning Templates • The “garbage gabage” example indicates: – A child can intuitively form a template for plurals (that is applicable in some human languages such as Bhasa Malaysia (e.g. kanak kanak=children) – A child can put anything in the placeholder X within the sentence template “Dad, Why X?” • But these hypotheses would need further evidence from First Language Acquistion
  • 11. Template Linearity • English – I love you. – I miss you. – I need you. • French – Je t’aime. – Tu me manques. – J’ai besoin de toi. Clearly, the linear order is very different between Constructions in different languages. This should entice us to think about how these constructions are generated.
  • 12. Semantic-Pragmatic Prompt • An area of overlap between the reason, context, and information content of some sentence. • Start with list of arguments (X1: I, X2: You) • I Want to express [+feeling] [+positive] [+distance], therefore: – in English, we invoke the template I miss X2. – In French, we invoke the template X2 me manques (with some adjustments depending on pronouns, etc) • So I can utter the sentence after filling the template: – I miss Randa. – Randa me manque.
  • 13. Template Variability • Almost everything can be said in an alternative way: – Godzilla destroyed the City, which is unfortunate. – It is unfortunate that Godzilla destroyed the city. – The destruction of the city by Godzilla is unfortunate. • So, there are different templates to express the relation between these four entities (being unfortunate, the destruction, Godzilla, the City). This again feeds into the argument of non- linearity of templates, this time within the same language.
  • 14. Template Malleability • Meaning how easy the template can be re- shaped. This includes the following: – Tense malleability: • John was eating fish. • John has been eating fish. – Synonym malleability: • Sarah cannot tolerate this any more. • Sarah cannot put up with this anymore. • The idea of malleability enables us to avoid accounting for hundreds of millions of combinations of basic templates.
  • 15. Using Templates • For information Extraction (e.g. Banko and Etzioni 2008), where templates where used to extract (is-a) relationships between entities.
  • 16. Using Templates in Machine Translation • Was first suggested by (Nagao, 1984) under the name of Example-Based Machine Translation. He also indicted this approach is relevant to Second Language Acquisition.
  • 17. Using Templates in Machine Translation • Current state of the art Phrase-Based Statistical Machine Translation techniques uses contiguous chunks. (Koehn, 2010)
  • 18. Using Templates in Machine Translation • But using contiguous chunks misses many phrases where there is a difference in word order between the two languages. - needs a lot of training data  • To compensate for this, a statistical reordering model is used - can make the output unintelligible 
  • 19. Using Templates in Machine Translation Chunk: Michael assumes that he will stay in the house -> Michael geht davon aus, dass er im haus bleibt Subchunks: Michael -> Michael in the house -> im haus So by removing (stenciling) subcunks from the chunk we get a translation template X1 assumes that he will stay X2 -> X1 geht davon aus, dass er X2 bleibt - preserves word order  - can apply to many sentences not seen before  - requires less training data  - can set restrictions on the type of placeholders (X1: NP , X2: PP) 
  • 20. •Thank X1! (X1 = You )