Lecture 19 Word Meanings II

Slides:



Advertisements
Similar presentations
Verbals and Verb Phrases
Advertisements

Natural Language Processing Semantic Roles. Semantics Road Map 1.Lexical semantics 2.Disambiguating words Word sense disambiguation Coreference resolution.
Lexical Semantics and Word Senses Hongning Wang
Creating a Similarity Graph from WordNet
Steven Schoonover.  What is VerbNet?  Levin Classification  In-depth look at VerbNet  Evolution of VerbNet  What is FrameNet?  Applications.
Linguistic Theory Lecture 8 Meaning and Grammar. A brief history In classical and traditional grammar not much distinction was made between grammar and.
Chapter 17. Lexical Semantics From: Chapter 17 of An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, by.
Lecture 19 Word Meanings II Topics Description Logic III Overview of MeaningReadings: Text Chapter 189NLTK book Chapter 10 March 27, 2013 CSCE 771 Natural.
Computational Semantics Ling 571 Deep Processing Techniques for NLP February 2, 2011.
LING 581: Advanced Computational Linguistics Lecture Notes April 6th.
November 20, 2003 Chapter 16 Lexical Semantics. Words have structured meanings Lexeme – a pairing of a form with a sense Orthographic form – the way the.
Structured lexicons and Lexical semantics Especially WordNet ® See D Jurafsky & JH Martin: Speech and Language Processing, Upper Saddle River NJ (2000):
C SC 620 Advanced Topics in Natural Language Processing Lecture Notes 2 1/20/04.
Lecture Lexical Semantics CS 4705.
Semantics. Philosophical Issues Context Context Reference Reference Deixis Deixis Structuralism Structuralism Linguistic Determinism Linguistic Determinism.
NATURAL LANGUAGE TOOLKIT(NLTK) April Corbet. Overview 1. What is NLTK? 2. NLTK Basic Functionalities 3. Part of Speech Tagging 4. Chunking and Trees 5.
Course G Web Search Engines 3/9/2011 Wei Xu
Lexical Semantics Read J & M Chapter 16. The task of classifying all the words of language, or what's the same thing, all the ideas that seek expression,
LEXICAL RELATION (2) TRUTH CONDITIONAL SEMANTICS:
Antonym Creation Tool Presented By Thapar University WordNet Development Team.
WORDNET Approach on word sense techniques - AKILAN VELMURUGAN.
Wordnet, Raw Text Pinker, continuing Chapter 2
PropBank, VerbNet & SemLink Edward Loper. PropBank 1M words of WSJ annotated with predicate- argument structures for verbs. –The location & type of each.
Lecture 18 Ontologies and Wordnet Topics Ontologies Wordnet Overview of MeaningReadings: Text 13.5 NLTK book Chapter 2 March 25, 2013 CSCE 771 Natural.
WordNet ® and its Java API ♦ Introduction to WordNet ♦ WordNet API for Java Name: Hao Li Uni: hl2489.
Oana Adriana Şoica Building and Ordering a SenDiS Lexicon Network.
Lecture 6 Hidden Markov Models Topics Smoothing again: Readings: Chapters January 16, 2013 CSCE 771 Natural Language Processing.
WORD SENSE DISAMBIGUATION STUDY ON WORD NET ONTOLOGY Akilan Velmurugan Computer Networks – CS 790G.
WORDNET. THE WORDNET SYSTEM  Lexicographer files  Code: Lexico files  database  Search Routines and Interfaces.
Lexical Semantics Chapter 16
Lecture 22 Word Similarity Topics word similarity Thesaurus based word similarity Intro. Distributional based word similarityReadings: NLTK book Chapter.
11 Chapter 19 Lexical Semantics. 2 Lexical Ambiguity Most words in natural languages have multiple possible meanings. –“pen” (noun) The dog is in the.
Semantic Role Labeling. Introduction Semantic Role Labeling AgentThemePredicateLocation.
Lecture 21 Computational Lexical Semantics Topics Features in NLTK III Computational Lexical Semantics Semantic Web USCReadings: NLTK book Chapter 10 Text.
Wordnet - A lexical database for the English Language.
Word Relations Slides adapted from Dan Jurafsky, Jim Martin and Chris Manning.
Deep structure (semantic) Structure of language Surface structure (grammatical, lexical, phonological) Semantic units have all meaning components such.
LING 6520: Comparative Topics in Linguistics (from a computational perspective) Martha Palmer Jan 15,
A FEW REVIEW EXERCISES Semantic Features. 1. Do the exercises found at: 1. NLP_mean1.html
An Applied Ontological Approach to Computational Semantics Sam Zhang.
◦ Process of describing the structure of phrases and sentences Chapter 8 - Phrases and sentences: grammar1.
Utkal University We Work On Image Processing Speech Processing Knowledge Management.
Lecture 24 Distributional Word Similarity II Topics Distributional based word similarity example PMI context = syntactic dependenciesReadings: NLTK book.
Lecture 19 Word Meanings II Topics Description Logic III Overview of MeaningReadings: Text Chapter 189NLTK book Chapter 10 March 27, 2013 CSCE 771 Natural.
Lecture 24 Distributiona l based Similarity II Topics Distributional based word similarityReadings: NLTK book Chapter 2 (wordnet) Text Chapter 20 April.
CROSSWORD PUZZLE – TEAM 2 Members:Derek van Assche Cody Hansen Jonathan Juett Seungbum Park Anthony Vito Date: 4/22/2014.
Word Meaning Reference vs. Sense Meaning relationships –Synonymy –Antonymy –Hyponymy.
Lexical Semantics and Word Senses Hongning Wang
Detecting and Exploiting Figurative Language in WordNet Wim Peters Department of Computer Science University of Sheffield.
WordNet Ontology Robert Lehman. WordNet What is WordNet? Why create WordNet? Word Relationships Limitation Applications and Related Projects RDF/OWL Demo.
Voice Lecture 9. Forms and Meanings Voice is a grammatical category of the verb, which reflects the semantic role of the verbal subject. This category.
Leonardo Zilio Supervisors: Prof. Dr. Maria José Bocorny Finatto
Lecture 24 Distributional Word Similarity II
Word Relations Slides adapted from Dan Jurafsky, Jim Martin and Chris Manning.
Lecture 21 Computational Lexical Semantics
Lecture 19 Word Meanings II
LING 581: Advanced Computational Linguistics
CSC 594 Topics in AI – Applied Natural Language Processing
Unit-4 Lexical Semantics M.B.Chandak, HoD CSE,
WordNet: A Lexical Database for English
Bulgarian WordNet Svetla Koeva Institute for Bulgarian Language
WordNet WordNet, WSD.
Lecture 7 HMMs – the 3 Problems Forward Algorithm
Word Relations Slides adapted from Dan Jurafsky, Jim Martin and Chris Manning.
Lecture 22 Word Similarity
CS224N Section 3: Corpora, etc.
LING/C SC 581: Advanced Computational Linguistics
Structure of a Lexicon Debasri Chakrabarti 13-May-19.
CS224N Section 3: Project,Corpora
Dynamic Word Sense Disambiguation with Semantic Similarity
Presentation transcript:

Lecture 19 Word Meanings II CSCE 771 Natural Language Processing Lecture 19 Word Meanings II Topics Description Logic III Overview of Meaning Readings: Text Chapter 189NLTK book Chapter 10 March 27, 2013

Overview Readings: Text 19 NLTK Book: Chapters 9 and 10 Last Time (Programming) Wordnet overview Today Computational Semantics Feature based grammars Readings: Text 19 NLTK Book: Chapters 9 and 10 Next Time: Computational Lexical Semantics

HW review Dropboxes Soon to exist: NER for handbook frequency distribution - Handbook Assignment Regular Expression /urllib2 - Identify prerequisites Assignment Extend backoff tagger to include trigram Assignment Test1

Wordnet Most synsets are connected to other synsets via a number of semantic relations. These relations vary based on the type of word, and include: Nouns hypernyms: Y is a hypernym of X if every X is a (kind of) Y (canine is a hypernym of dog) “superordinate” “superclass” hyponyms: Y is a hyponym of X if every Y is a (kind of) X (dog is a hyponym of canine) “IS-A” coordinate terms: Y is a coordinate term of X if X and Y share a hypernym (wolf is a coordinate term of dog, and dog is a coordinate term of wolf) “sibling” holonym: Y is a holonym of X if X is a part of Y (building is a holonym of window) “HAS-PART” meronym: Y is a meronym of X if Y is a part of X (window is a meronym of building) “IS-PART” “IS-MEMBER” http://en.wikipedia.org/wiki/WordNet

Verbs Adjectives Adverbs hypernym: the verb Y is a hypernym of the verb X if the activity X is a (kind of) Y (to perceive is an hypernym of to listen) troponym: the verb Y is a troponym of the verb X if the activity Y is doing X in some manner (to lisp is a troponym of to talk) entailment: the verb Y is entailed by X if by doing X you must be doing Y (to sleep is entailed by to snore) coordinate terms: those verbs sharing a common hypernym (to lisp and to yell) Adjectives related nouns similar to participle of verb Adverbs root adjectives http://en.wikipedia.org/wiki/WordNet

http://wordnet.princeton.edu/ x

Wordnet online Fig 19-1

Word senses A word sense is a distinct meaning Synonym sets are relations among word senses couch/sofa, car/automobile antonyms also long/short, big/large, rise/fall extremes; or opposite in direction

Fig 19-2 Noun relations in wordnet

Fig 19-3 Verb relations in wordnet

Fig19-4-like IS-A (hyponym) Chain for lemma bass#7

Sister terms (= coordinate terms)

Thematic Roles 19.19 “Sasha broke the window.” exists e,x,y breaking(e) & breaker(e, Sasha) & brokenThing(e, y) & window(y) 19.20 Pat opened the door. Deep or thematic roles Panini (Indian grammarian) circa 7th-4th century BC Fillmore 1968, Gruber 1965

Fig 19.5 Common Thematic Roles

19.6 Examples of Thematic Roles

Variations of expression John broke the window. John broke the window with a rock. The rock broke the window. The window broke. The window was broken by John.

Case Frames for verbs Break Agent: Subject, Theme:Object Agent: Subject, Theme:Object, Instrument: PP-with Instrument:Subject, Theme:Object Theme: Subject

19.4.3 Problems with Thematic Roles Example 19.27 the cook opened the jar with the new gadget. the new gadget opened the jar. Example 19.28 Shelly ate the banana with a fork. *The fork ate the banana.

Prop Bank PropBank is a corpus that is annotated with verbal propositions and their arguments—a "proposition bank". http://verbs.colorado.edu/~mpalmer/projects/ace.html http://en.wikipedia.org/wiki/PropBank

PropBank Online http://verbs.colorado.edu/~mpalmer/projects/ace.html

FrameNet

Framenet Core Roles

FrameNet

Selectional restrictions of roles from PropBank

Fig 19-7 Hamburger Edible?

Figure 19.8 Shank’s Conceptual Dependencies