Скачать презентацию CS 626 449 Speech NLP and the Web Topics Скачать презентацию CS 626 449 Speech NLP and the Web Topics

317a982fc5f7b5cf2deae4f3cd6f9bc0.ppt

  • Количество слайдов: 46

CS 626/449 : Speech, NLP and the Web/Topics in AI Programming (Lecture 4: Word CS 626/449 : Speech, NLP and the Web/Topics in AI Programming (Lecture 4: Word Sense Disambiguation; Wordnet) Pushpak Bhattacharyya CSE Dept. , IIT Bombay

Word Sense Disambiguation • WSD is a well know difficult problem • Questions: Should Word Sense Disambiguation • WSD is a well know difficult problem • Questions: Should the approach be – Knowledge based – Statistical – Combined • Resources – Sense marked (annotated corpora) – Sense repository • Training – Unsupervised – Semi supervised

Synonym Distribution principle: Words A and B are called ‘synonyms’ if their distribution is Synonym Distribution principle: Words A and B are called ‘synonyms’ if their distribution is identical in a corpus. That means they can replace each other in any context. (Strong requirement – ideal) Pure synonym: If A and B are synonyms in all context (can replace in all contexts) they are pure synonyms. It has been very difficult to find pure synonyms. Question: How to ensure replaceability in – – Syntax Semantics Pragmatics Discourse

Example of replaceability Consider {mother, mummi, amma} 1. Syntax – yes: mother, mummi, ammi Example of replaceability Consider {mother, mummi, amma} 1. Syntax – yes: mother, mummi, ammi – noun: ex. Mother smiles. 1. 2. Constituent Parse Tree Dependency Parse agent mother S S S smiles S S Mother smiles 2. Semantics: (Semantic Roles) replaceable 3. Pragmatics: register (fails) 1. 2. A formal situation, ex. Dear Sir, Grant me leave for one day as my mother has to undergo an operation A proverb, ex. Mother makes the nation Register is linguistic memory specific to a situation

Relational and Componential Semantics Relational Semantics (Words can disambiguate each other) vs. Componential Semantics Relational and Componential Semantics Relational Semantics (Words can disambiguate each other) vs. Componential Semantics (Words need features for disambiguation) Cat Example animal An expert Possible Features: Animate, Human, Carnivorous, Small, Moving Componential Semantics Semantic Feature Vector for cat (animal): <1, 0, 1, 1, 1> cat (expert): <1, 1, U, U, 1> Relational Semantics cat (animal): {cat, feline} cat (expert): {cat, expert}

What is Wordnet What is Wordnet

Wordnet • A lexical knowledgebased on conceptual lookup • Organizing concepts in a semantic Wordnet • A lexical knowledgebased on conceptual lookup • Organizing concepts in a semantic network. • Organize lexical information in terms of word meaning, rather than word form • Wordnet can also be used as a thesaurus.

Psycholinguistic Theory • Human lexical memory for nouns as a hierarchy. • • • Psycholinguistic Theory • Human lexical memory for nouns as a hierarchy. • • • Can canary sing? - Pretty fast response. Can canary fly? - Slower response. Does canary have skin? – Slowest response. Animal (can move, has skin) Bird (can fly) canary (can sing) Wordnet - a lexical reference system based on psycholinguistic theories of human lexical memory.

Lexical Matrix Lexical Matrix

Wordnet - Lexical Matrix (with examples) Word Forms Word Meanings F 1 M 2 Wordnet - Lexical Matrix (with examples) Word Forms Word Meanings F 1 M 2 M 3 … Mm (depend) E 1, 1 F 2 F 3 (bank) E 1, 2 (rely) E 1, 3 Fn (embankme nt) E 2, … (bank) E 2, 2 (bank) E 3, 2 … E 3, 3 … Em, n

Wordnet: International Scenario • Wordnet is a network of words linked by lexical and Wordnet: International Scenario • Wordnet is a network of words linked by lexical and semantic relations. • The first wordnet in the world was for English developed at Princeton over 15 years. • The Eurowordnet- linked structure of European language wordnets was built in 1998 over 3 years with funding from the EC as a a mission mode project. • Wordnets for Hindi and Marathi being built at IIT Bombay are amongst the first IL wordnets. • All these are proposed to be linked into the Indo. Wordnet which eventually will be linked to the English and the Euro wordnets.

Linked Wordnets in India Bengali Wordnet Dravidian Language Wordnets Sanskrit Wordnet Punjabi Wordnet Hindi Linked Wordnets in India Bengali Wordnet Dravidian Language Wordnets Sanskrit Wordnet Punjabi Wordnet Hindi Wordnet North East Language Wordnet Konkani Wordnet Marathi Wordnet English Wordnet

Great Linguistic Diversity • • Major streams – Indo European – Dravidian – Sino Great Linguistic Diversity • • Major streams – Indo European – Dravidian – Sino Tibetan – Austro-Asiatic Some languages are ranked within 20 in the world in terms of the populations speaking them – Hindi and Urdu: 5 th (~500 milion) – Bangla: 7 th (~300 million) – Marathi 14 th (~70 million)

Major Language Processing Initiatives • Mostly from the Government: Ministry of IT, Ministry of Major Language Processing Initiatives • Mostly from the Government: Ministry of IT, Ministry of Human Resource Development, Department of Sceince and Technology • Recently great drive from the industry: NLP efforts with Indian language in focus – Google – Microsoft – IBM Research Lab – Yahoo – TCS

Fundamental Design Question • Syntagmatic vs. Paradigmatic realtions? • Psycholinguistics is the basis of Fundamental Design Question • Syntagmatic vs. Paradigmatic realtions? • Psycholinguistics is the basis of the design. • When we hear a word, many words come to our mind by association. • For English, about half of the associated words are syntagmatically related and half are paradignatically related. • For cat – animal, mammal- paradigmatic – mew, purr, furry- syntagmatic

Stated Fundamental Application of Wordnet: Sense Disambiguation Determination of the correct sense of the Stated Fundamental Application of Wordnet: Sense Disambiguation Determination of the correct sense of the word The crane ate the fish vs. The crane was used to lift the load bird vs. machine

The problem of Sense tagging • Given a corpora To Assign correct sense to The problem of Sense tagging • Given a corpora To Assign correct sense to the words. • This is sense tagging. Needs Word Sense Disambiguation (WSD) • Highly important for Question Answering, Machine Translation, Text Mining tasks.

Basic Principle • Words in natural languages are polysemous. • However, when synonymous words Basic Principle • Words in natural languages are polysemous. • However, when synonymous words are put together, a unique meaning often emerges. • Use is made of Relational Semantics. • Componential Semantics where each word is a bundle of semantic features (as in the Schankian Conceptual Dependency system or Lexical Componential Semantics) is to be examined as a viable alternative.

Componential Semantics • Consider cat and tiger. Decide on componential attributes. Furry Carnivorous Heavy Componential Semantics • Consider cat and tiger. Decide on componential attributes. Furry Carnivorous Heavy • For cat (Y, Y, N, Y) • For tiger (Y, Y, Y, N) Complete and correct Attributes are difficult to design. Domesticable

Semantic relations in wordnet 1. Synonymy 2. Hypernymy / Hyponymy 3. Antonymy 4. Meronymy Semantic relations in wordnet 1. Synonymy 2. Hypernymy / Hyponymy 3. Antonymy 4. Meronymy / Holonymy 5. Gradation 6. Entailment 7. Troponymy 1, 3 and 5 are lexical (word to word), rest are semantic (synset to synset).

Synset: the foundation (house) 1. house -- (a dwelling that serves as living quarters Synset: the foundation (house) 1. house -- (a dwelling that serves as living quarters for one or more families; "he has a house on Cape Cod"; "she felt she had to get out of the house") 2. house -- (an official assembly having legislative powers; "the legislature has two houses") 3. house -- (a building in which something is sheltered or located; "they had a large carriage house") 4. family, household, house, home, menage -- (a social unit living together; "he moved his family to Virginia"; "It was a good Christian household"; "I waited until the whole house was asleep"; "the teacher asked how many people made up his home") 5. theater, theatre, house -- (a building where theatrical performances or motion-picture shows can be presented; "the house was full") 6. firm, house, business firm -- (members of a business organization that owns or operates one or more establishments; "he worked for a brokerage house") 7. house -- (aristocratic family line; "the House of York") 8. house -- (the members of a religious community living together) 9. house -- (the audience gathered together in a theatre or cinema; "the house applauded"; "he counted the house") 10. house -- (play in which children take the roles of father or mother or children and pretend to interact like adults; "the children were playing house") 11. sign of the zodiac, star sign, mansion, house, planetary house -- ((astrology) one of 12 equal areas into which the zodiac is divided) 12. house -- (the management of a gambling house or casino; "the house gets a percentage of every bet")

Synset: DSF format (1/2) • Synset ID: a unique number identifying a synset • Synset: DSF format (1/2) • Synset ID: a unique number identifying a synset • Category: POS category of the words • Concept: The part of the gloss that gives a brief summary of what the synset represents • Example: One or more examples of the words in the synset being used in sentences • Synset: The set of synonymous words comprised in the synset

Synset - DSF format (2/2) ID : : 121 CATEGORY : : NOUN CONCEPT Synset - DSF format (2/2) ID : : 121 CATEGORY : : NOUN CONCEPT : : अपन स छ ट क परत हदय म उठनव ल परम EXAMPLE : : “च च नहर क बचच स बहत ह सनह थ ” SYNSET : : सनह , लग व , ममत

Creation of Synsets Three principles: • Minimality • Coverage • Replacability Creation of Synsets Three principles: • Minimality • Coverage • Replacability

Synset creation (continued) Home John’s home was decorated with lights on the occasion of Synset creation (continued) Home John’s home was decorated with lights on the occasion of Christmas. Having worked for many years abroad, John Returned home. House John’s house was decorated with lights on the occasion of Christmas. Mercury is situated in the eighth house of John’s horoscope.

Synsets (continued) {house} is ambiguous. {house, home} has the sense of a social unit Synsets (continued) {house} is ambiguous. {house, home} has the sense of a social unit living together; Is this the minimal unit? {family, house , home} will make the unit completely unambiguous. For coverage: {family, household, house, home} ordered according to frequency. Replacability of the most frequent words is a requirement.

Synset creation From first principles – Pick all the senses from good standard dictionaries. Synset creation From first principles – Pick all the senses from good standard dictionaries. – Obtain synonyms for each sense. – Needs hard and long hours of work.

Synset creation (continued) From the wordnet of another language in the same family – Synset creation (continued) From the wordnet of another language in the same family – Pick the synset and obtain the sense from the gloss. – Get the words of the target language. – Often same words can be used- especially for t%sama words. – Translation, Insertion and deletion. Hindi Synset: Anau. Bava. I jaanakar ma. Mjaa hu. Aa (experienced person) Marathi Synset: Anau. Bava. I t& jaa. Nata &ata

Gloss and Example Crucially needed for concept explication, wordnet building using another wordnet and Gloss and Example Crucially needed for concept explication, wordnet building using another wordnet and wordnet linking. {earthquake, temblor, seism} -- (shaking and vibration at the surface of the earth resulting from underground movement along a fault plane of from volcanic activity)

Semantic Relations • Hypernymy and Hyponymy – Relation between word senses (synsets) – X Semantic Relations • Hypernymy and Hyponymy – Relation between word senses (synsets) – X is a hyponym of Y if X is a kind of Y – Hyponymy is transitive and asymmetrical – Hypernymy is inverse of Hyponymy (lion->animal->animate entity->entity)

Semantic Relations (continued) • Meronymy and Holonymy – Part-whole relation, branch is a part Semantic Relations (continued) • Meronymy and Holonymy – Part-whole relation, branch is a part of tree – X is a meronymy of Y if X is a part of Y – Holonymy is the inverse relation of Meronymy {kitchen} ……………. {house}

Lexical Relation • Antonymy – Oppositeness in meaning – Relation between word forms – Lexical Relation • Antonymy – Oppositeness in meaning – Relation between word forms – Often determined by phonetics, word length etc. ({rise, ascend} vs. {fall, descend})

Troponym and Entailment • Entailment {snoring – sleeping} • Troponym {limp, strut – walk} Troponym and Entailment • Entailment {snoring – sleeping} • Troponym {limp, strut – walk} {whisper – talk}

Entailment. Snoring entails sleeping. Buying entails paying. • Proper Temporal Inclusion can be in Entailment. Snoring entails sleeping. Buying entails paying. • Proper Temporal Inclusion can be in any way. Sleeping temporally includes snoring. Buying temporally includes paying. • Co-extensiveness. (Troponymy) Limping is a manner of walking.

Opposition among verbs. • {Rise, ascend} {fall, descend} Tie-untie (do-undo) Walk-run (slow, fast) Teach-learn Opposition among verbs. • {Rise, ascend} {fall, descend} Tie-untie (do-undo) Walk-run (slow, fast) Teach-learn (same activity different perspective) Rise-fall (motion upward or downward) • Opposition and Entailment. Hit or miss (entail aim). Backward presupposition. Succeed or fail (entail try. )

The causal relationship. Show- see. Give- have. Causation and Entailment. Giving entails having. Feeding The causal relationship. Show- see. Give- have. Causation and Entailment. Giving entails having. Feeding entails eating.

Kinds of Antonymy Size Quality State Personality Direction Amount Place Time Gender Small - Kinds of Antonymy Size Quality State Personality Direction Amount Place Time Gender Small - Big Good – Bad Warm – Cool Dr. Jekyl- Mr. Hyde East- West Buy – Sell Little – A lot Far – Near Day - Night Boy - Girl

Kinds of Meronymy Component-object Head - Body Staff-object Wood - Table Member-collection Tree - Kinds of Meronymy Component-object Head - Body Staff-object Wood - Table Member-collection Tree - Forest Feature-Activity Speech - Conference Place-Area Palo Alto - California Phase-State Youth - Life Resource-process Pen - Writing Actor-Act Physician Treatment

Gradation State Childhood, Youth, Old age Temperature Hot, Warm, Cold Action Sleep, Doze, Wake Gradation State Childhood, Youth, Old age Temperature Hot, Warm, Cold Action Sleep, Doze, Wake

Word. Net Sub-Graph (English) Hyponymy Dwelling, abode Hypernymy Meronymy kitchen Hyponymy bckyard veranda M Word. Net Sub-Graph (English) Hyponymy Dwelling, abode Hypernymy Meronymy kitchen Hyponymy bckyard veranda M e r o n y m y bedroom house, home Gloss A place that serves as the living quarters of one or mor efamilies Hyponymy study guestroom hermitage cottage

Word. Net Sub-Graph: Hindi च प य , पश (chaupaayaa, pashu) Four-legged animal श Word. Net Sub-Graph: Hindi च प य , पश (chaupaayaa, pashu) Four-legged animal श क ह र )shaakaahaarii( herbivorous Hypernym पछ (puunchh ) Tail थन (thana) udder m e r o n y m ग य , गऊ )gaaya , gauu) Cow Attribute Gloss Hyponym स गव ल एक श क ह र म द च प य (siingwaalaa eka sakaahaarii maadaa choupaayaa) A horny, herbivorous, four-legged female animal) Ability Verb पगर न ( paguraanaa( ruminate Antonym क मधन kaamadhenu A kind of cow मन ग य mainii gaaya A kind of cow बल (baila( Ox

Wordnet Subgraph (Marathi) वनसपत र न HYPERNYMY ख ड म ळ M E R Wordnet Subgraph (Marathi) वनसपत र न HYPERNYMY ख ड म ळ M E R O N Y M Y झ ड , वकष तर , HYPONYMY ल ब H O L O N Y M Y आब GLOSS ब ग मळ , ख ड , फ दय , प न इतय द न यकत अस वनसपत व शष : "झ ड परय वरण शदध करणय च क म करत त "

Pan-India Dictionary Standard Senses Hindi Marathi Bangali Oriya Tamil (W 1, W 2, W Pan-India Dictionary Standard Senses Hindi Marathi Bangali Oriya Tamil (W 1, W 2, W 3, W 4, W 5, W 6 ) (W 1, W 2, W 3) (W 1, W 2, W 3, W 4) (W 1, W 2, W 3) (sun( )सरय , सरज , भ न भ सकर , परभ कर . . … … … अशम न (cub, laddie, sonny boy) (son, boy) (लडक छ कड छ कर , अशम ल , , द नकर , ) , ब लक , बचच , छ र , , ल ड ) , पतर , बट , लडक , ल ल , सत , बचच , नदन , पत , च रज व , च रज ( ) )सरय , भ न , द व कर , भ सकर रव , द नश , द नमण ( , मलग , प रग प र , प रग ) , ( मलग , पतर लक , च रज व तनय ) ( , ,

Sanskrit Wordnet: a new effort- A column in the Concept based Multilingual dictionary Concepts Sanskrit Wordnet: a new effort- A column in the Concept based Multilingual dictionary Concepts L 1 (English) L 2 (Hindi) L 3 (Sanskrit) Concept ID: Concept description (W 1, W 2, W 3, . . ) (W 4, W 5, W 6, . . ) (W 7, W 8, W 9, . . ) (बदर , बनदर , ब नर , व नर , क श , कप , मरकट , . . ) (व नर , कप , पलवङग , पलवग , श ख मग , वल मख , मरकट , . . ) 4066: any of various long-tailed primates (monkey) (excluding the prosimians) 2186: a typical star that is the source of light and heat (sun) for the planets in the solar system (सरय , सरज , भ न , द व कर , भ सकर , परभ कर , द नकर , रव , (सरय , सव त , आद तय , म तर , अरण , भ न ,

Summary • Synsets: basic units • Principles of creation: minimality, coverage, replaceability • Semantic Summary • Synsets: basic units • Principles of creation: minimality, coverage, replaceability • Semantic relations (main ones): hypernymy (is -a), meronymy (part-of), antomymy, troponymy (manner-of)