The Practical Value of Statistics for Sentence Generation: The Perspective of the Nitrogen System Irene Langkilde-Geary.

Slides:



Advertisements
Similar presentations
Social Communication Three to Six Years Old. Goal: Use words, phrases and sentences to inform, direct, ask questions and express anticipation, imagination,
Advertisements

Language and Grammar Unit
Computational language: week 10 Lexical Knowledge Representation concluded Syntax-based computational language Sentence structure: syntax Context free.
 Christel Kemke 2007/08 COMP 4060 Natural Language Processing Feature Structures and Unification.
CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 2 (06/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Part of Speech (PoS)
CPSC 422, Lecture 16Slide 1 Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 16 Feb, 11, 2015.
Semantics (Representing Meaning)
Lexical Functional Grammar History: –Joan Bresnan (linguist, MIT and Stanford) –Ron Kaplan (computational psycholinguist, Xerox PARC) –Around 1978.
Albert Gatt Corpora and Statistical Methods Lecture 12.
Page 1 SRL via Generalized Inference Vasin Punyakanok, Dan Roth, Wen-tau Yih, Dav Zimak, Yuancheng Tu Department of Computer Science University of Illinois.
Grammatical Relations and Lexical Functional Grammar Grammar Formalisms Spring Term 2004.
Statistical NLP: Lecture 3
Natural Language Processing - Feature Structures - Feature Structures and Unification.
 Christel Kemke 2007/08 COMP 4060 Natural Language Processing Word Classes and English Grammar.
Artificial Intelligence 2005/06 From Syntax to Semantics.
 Christel Kemke 2007/08 COMP 4060 Natural Language Processing Feature Structures and Unification.
NLP and Speech 2004 English Grammar
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Outline of English Syntax.
Some slides adapted from.  Linguistic Generation  Statistical Generation.
English grammar English 301.
1 A Chart Parser for Analyzing Modern Standard Arabic Sentence Eman Othman Computer Science Dept., Institute of Statistical Studies and Research (ISSR),
Lecture 1, 7/21/2005Natural Language Processing1 CS60057 Speech &Natural Language Processing Autumn 2005 Lecture 1 21 July 2005.
GRAMMAR APPROACH By: Katherine Marzán Concepción EDUC 413 Prof. Evelyn Lugo.
Grammar Skills Workshop
Chapter 4 Basics of English Grammar Business Communication Copyright 2010 South-Western Cengage Learning.
Lecture 12: 22/6/1435 Natural language processing Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
Natural Language Processing Lecture 6 : Revision.
CS : Language Technology for the Web/Natural Language Processing Pushpak Bhattacharyya CSE Dept., IIT Bombay Constituent Parsing and Algorithms (with.
Copy right 2003 Adam Pease permission to copy granted so long as slides and this notice are not altered Language to Logic Translation.
Syntax Why is the structure of language (syntax) important? How do we represent syntax? What does an example grammar for English look like? What strategies.
Ideas for 100K Word Data Set for Human and Machine Learning Lori Levin Alon Lavie Jaime Carbonell Language Technologies Institute Carnegie Mellon University.
For Wednesday Read chapter 23 Homework: –Chapter 22, exercises 1,4, 7, and 14.
Linguistic Essentials
Culture , Language and Communication
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
The Greek Verb System: A Bird’s Eye View Chapter 2.
CSA2050 Introduction to Computational Linguistics Parsing I.
CSE573 Autumn /23/98 Natural Language Processing Administrative –PS3 due today –PS4 out Wednesday, due Friday 3/13 (last day of class) special.
Artificial Intelligence 2004
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Spring 2006-Lecture 2.
Leonid Iomdin Institute for Information Transmission Problems, Russian Academy of Sciences
SYNTAX.
NLP. Introduction to NLP (U)nderstanding and (G)eneration Language Computer (U) Language (G)
 2003 CSLI Publications Ling 566 Oct 17, 2011 How the Grammar Works.
Basic Syntactic Structures of English CSCI-GA.2590 – Lecture 2B Ralph Grishman NYU.
October 10, 2003BLTS Kickoff Meeting1 Transfer with Strong Decoding Learning Module Transfer Rules {PP,4894} ;;Score: PP::PP [NP POSTP] -> [PREP.
NATURAL LANGUAGE PROCESSING
September 26, : Grammars and Lexicons Lori Levin.
SYNTACTIC DEVELOPMENT ECSE 500 CLASS SESSION 6. REVIEW PHONOLOGY SEMANTICS MORPHOLOGY TODAY - SYNTAX.
A Simple English-to-Punjabi Translation System By : Shailendra Singh.
Inflection. Inflection refers to word formation that does not change category and does not create new lexemes, but rather changes the form of lexemes.
Expanding verb phrases
SYNTAX.
Child Syntax and Morphology
Grammar Grammar analysis.
Morphology Morphology Morphology Dr. Amal AlSaikhan Morphology.
CSC 594 Topics in AI – Natural Language Processing
Lecture – VIII Monojit Choudhury RS, CSE, IIT Kharagpur
Statistical NLP: Lecture 3
Semantics (Representing Meaning)
ALL ABOUT VERBS GRAMMAR SUMMARY.
Telegraphic speech: two- and three-word utterances
Chapter 4 Basics of English Grammar
CS4705 Natural Language Processing
Linguistic Essentials
Chapter 4 Basics of English Grammar
A Teaching Plan Presentation
Artificial Intelligence 2004 Speech & Natural Language Processing
Meanings of the voices active: The subject acts. passive:
Presentation transcript:

The Practical Value of Statistics for Sentence Generation: The Perspective of the Nitrogen System Irene Langkilde-Geary

How well do statistical n-grams make linguistic decisions? Subject-Verb Agreement Article-Noun Agreement I am 2797 a trust 394 an trust 0 the trust 1355 I are 47 a trusts 2 an trusts 0 the trusts 115 I is 14 Singular vs Plural Word Choice their trust 28 reliance 567 trust 6100 their trusts 8 reliances 0 trusts 1083

More Examples Relative pronoun Preposition visitor who 9 visitors who 20 in Japan 5413 to Japan 1196 visitor which 0 visitors which 0 visitor that 9 visitors that 14 came to 2443 arrived in 544 came in 1498 arrived to 35 Singular vs Plural came into 244 arrived into 0 visitor 575 visitors 1083 came to Japan 7 arrived to Japan 0 Verb Tense came into Jap 1 arrived into Japan 0 admire 212 admired 211 came in Japan 0 arrived in Japan 4 admires 107

How can we get a computer to learn by “reading”?

Nitrogen takes a two-step approach 1.Enumerate all possible expressions 2.Rank them in order of probabilistic likelihood Why two steps? They are independent.

Assigning probabilities Ngram model Formula for bigrams: P(S) = P(w 1 | START ) * P(w 2 |w 1 ) * … * P(w n |w n-2 ) Probabilistic syntax (current work) –A variant of probabilistic parsing models

Sample Results of Bigram model Random path : (out of a set of 11,664,000 semantically-related sentences) Visitant which came into the place where it will be Japanese has admired that there was Mount Fuji. Top three: Visitors who came in Japan admire Mount Fuji. Visitors who came in Japan admires Mount Fuji. Visitors who arrived in Japan admire Mount Fuji. Strengths Reflects reality that 55% (Stolke et al. 1997) of dependencies are binary, and between adjacent words Embeds linear ordering constraints

Limitations of Bigram model Example Reason Visitors come in Japan. A three-way dependency He planned increase in sales. Part-of-speech ambiguity A tourist who admire Mt. Fuji... Long-distance dependency A dog eat/eats bone. Previously unseen ngrams I cannot sell their trust. Nonsensical head-arg relationship The methods must be modified to Improper subcat structure the circumstances.

Representation of enumerated possibilities (Easily on the order of to or more) List Lattice Forest Issues space/time constraints redundancy localization of dependencies non-uniform weights of dependencies

Number of phrases versus size (in bytes) for 15 sample inputs

Number of phrases versus time (in seconds) for 15 sample inputs

Generating from Templates and Meaning-based Inputs INPUT  ( VALUE ) -OR- VALUE  INPUT -OR- Labels are defined in: 1.input 2.user-defined lexicon 3.WordNet-based lexicon (~ 100,000 concepts) Example Input: (a1 :template (a2 / “eat” :agent YOU :patient a3) :filler (a3 / |poulet| ))

Mapping Rules 1.Recast one input to another –(implicitly providing varying levels of abstraction) 2.Assign linear order to constituents 3.Add missing info to under-specified inputs Matching Algorithm Rule order determines priority. Generally: –Recasting < linear ordering < under-specification –High (more semantic) level of abstraction < low (more syntactic) –Distant position (adjuncts) from head < near (complements) –Basic properties < specialized

Recasting (a1 :venue :cusine ) (a2 / |serve| :agent :patient ) (a2 / |have the quality of being| :domain (a3 / “food type” :possessed-by ) :range (b1 / |cuisine|))

Recasting (a1 :venue :region ) (a2 / |serve| :agent :patient (a3 / |serve| :voice active :subject :object ) (a3 / |serve| :voice passive :subject :adjunct (b1 / :anchor |BY| ))

Linear ordering (a3 / |serve| :voice active :subject :object ) ( a4 / |serve| :voice active :object )

Under-specification (a4 / |serve|) (a5 / |serve| :cat verb) (a6 / |serve| :cat noun)

Under-specification (a4 / |serve|) (a5 / |serve| :cat verb) (a5 / |serve| :cat verb :tense past) (a5 / |serve| :cat verb :tense present)

Core features currently recognized by Nitrogen Syntactic relations :subject :object :dative :compl :pred :adjunct :anchor :pronoun :op :modal :taxis :aspect :voice :article Functional relations :logical-sbj :logical-obj :logical-dat :obliq1 :obliq2 :obliq3 :obliq2-of :obliq3- of :obliq1-of :attr :generalized-possesion :generalized-possesion-inverse Semantic/Systemic Relations :agent :patient :domain :domain-of :condition :consequence :reason :compared-to :quant :purpose :exemplifier :spatial-locating :temporal-locating :temporal-locating-of :during :destination :means :manner :role :role-of-agent :source :role-of-patient :inclusive :accompanier :sans :time :name :ord Dependency relations :arg1 :arg2 :arg3 :arg1-of :arg2-of :arg3-of

Properties used by Nitrogen :cat [nn, vv, jj, rb, etc.] :polarity [+, -] :number [sing, plural] :tense [past, present] :person [1s 2s 3s 1p 2p 3p s p all] :mood [indicative, pres-part, past-part, infinitive, to-inf, imper]

How many grammar rules needed for English? Sentence  Constituent+ Constituent  Constituent+ OR Leaf Leaf  Punc* FunctionWord* ContentWord FunctionWord* Punc* FunctionWord  ``and'' OR ``or'' OR ``to'' OR ``on'' OR ``is'' OR ``been'' OR ``the'' OR …. ContentWord  Inflection(RootWord,Morph) RootWord  ``dog'' OR ``eat'' OR ``red'' OR.... Morph  none OR plural OR third-person-singular...

Computational Complexity (x 2 /A 2 ) + (y 2 /B 2 ) = 1 X Y ???

Advantages of a statistical approach for symbolic generation module Shifts focus from “grammatical” to “possible” Significantly simplifies knowledge bases Broadens coverage Potentially improves quality of output Dramatically reduces information demands on client Greatly increases robustness