DOC PREVIEW
MSU CSE 842 - Natural Language Processing
Course Cse 842-
Pages 14

This preview shows page 1-2-3-4-5 out of 14 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 14 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 14 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 14 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 14 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 14 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 14 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

3/16/2011 CSE842, Spring 2011, MSU 1CSE842: Natural Language ProcessingLecture 16: Lexical Semantics3/16/2011 CSE842, Spring 2011, MSU 2What is lexical semantics?• Meaning of Words• Lexical Relations• WordNet• Thematic Roles• Selectional Restrictions3/16/2011 CSE842, Spring 2011, MSU 3Lexeme• Lexeme is an entry in the lexicon that includes– an orthographic representation– a phonological form– a symbolic meaning representation or sense• Lemma: – Grammatical form to represent lexeme• book is the lemma for books. • Lemmatization: process of mapping from a wordform to a lemma – Depends on the context3/16/2011 CSE842, Spring 2011, MSU 4Lexeme• Dictionary entries:–Red n: the color of blood or a ruby– Blood n: the red liquid that circulates in the heart, arteries and veins of animals– Right adj: located nearer the right hand esp. being on the right when facing the same direction as the observer–Left adj: located nearer to this side of the body than the right3/16/2011 CSE842, Spring 2011, MSU 5• Do dictionaries give us definitions?– Some are circular– All are defined in terms of other lexemes– You have to know something to learn something• What can we learn from dictionaries?– Relations between words:• Oppositions, similarities, hierarchies3/16/2011 CSE842, Spring 2011, MSU 6Homonomy• Homonyms: Words with same form but different, unrelated meanings, or senses (multiple lexemes)– A bank holds investments in a custodial account in the client’s name.– As agriculture is burgeoning on the east bank, the river will shrink even more• Similar phenomena– homophones - read and red (different orth. form)– homographs - bass and bass (different phon. form)3/16/2011 CSE842, Spring 2011, MSU 7Polysemy?• Word with multiple but related meanings (same lexeme)– They rarely serve red meat.– He served as U.S. ambassador.– He might have served his time in prison.• What’s the difference between polysemy and homonymy?– Homonymy: distinct, unrelated meanings– Polysemy: distinct but related meaning– Different etymology? –zeugma? •? Does Midwest Express serve breakfast and Detroit?3/16/2011 CSE842, Spring 2011, MSU 8Synonomy• Substitutability: different lexemes with the same meaning– How big is that plane?– How large is that plane?– How big are you? Big brother is watching.• What influences substitutability?– Polysemy (large vs. old sense)– register: He’s really cheap/?parsimonious.– collocational constraint: roast beef, ?baked beef– convention: economy fare/?price3/16/2011 CSE842, Spring 2011, MSU 9Hyponomy• General: hypernym (superordinate)– “vehicle” is a hypernym of “car”• Specific: hyponym (underneath)– “car” is a hyponym of “vehicle”• Test: That is a car implies that is a vehicle• What is ontology? Object in some domain• What is taxonomy? Structuring of those objects• What is object hierarchy? Structured hierarchy that supports feature inheritance3/16/2011 CSE842, Spring 2011, MSU 10WordNet• Lexical database– George Miller et al. at Princeton– http://www.cogsci.princeton.edu/~wn– Most widely used hierarchically organized lexical database for English– Synset: set of synonyms, a dictionary-style definition (or gloss), and some examples of uses --> a concept– Databases for nouns, verbs, and modifiers (adjectives & adverbs)• Lexical relationships are implemented as semantic networks, where applications can traverse to find synonyms, antonyms, hierarchies,...3/16/2011 CSE842, Spring 2011, MSU 11WordNet3/16/2011 CSE842, Spring 2011, MSU 123/16/2011 CSE842, Spring 2011, MSU 13Noun Relations in WordNet3/16/2011 CSE842, Spring 2011, MSU 14Verb Relations in WordNet3/16/2011 CSE842, Spring 2011, MSU 15Event Participants• An important aspect of lexical meaning has to do with the semantics of events. • Predicate-argument structure represents an event– neo-Davidsonian reification of events• Semantic constraints on the arguments of event predicates: – Semantic roles: thematic roles– Selectional restriction 3/16/2011 CSE842, Spring 2011, MSU 16Thematic Roles• John broke a glass• Mary opened a jar∃e,y, Breaking(e) ^ Breaker(e, John ) ^ BrokenThing(e,y) ^ GlassWare(y)∃e,y, Opening(e) ^ Opener(e, Mary ) ^ OpenedThing(e,y) ^ Container(y)3/16/2011 CSE842, Spring 2011, MSU 17Thematic RolesA set of roles:– agent, theme: John broke a glass– experiencer: John broke an angle in the football game– force, result, content, instrument, beneficiary, source, goal,...The dog ate the cheeseburger.What is cheeseburger?The sniper shot his victim with a rifle.What is rifle?3/16/2011 CSE842, Spring 2011, MSU 18Thematic Roles3/16/2011 CSE842, Spring 2011, MSU 19Thematic Roles3/16/2011 CSE842, Spring 2011, MSU 20Diathesis Alternation• Many verbs allow their thematic roles to be realized in various syntactic positions– 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• VerbNet: an online resource that provides references to a large set of English verbs and the semantic classes they belong and the various altrenations in which they participate. – http://verbs.colorado.edu/~mpalmer/projects/verbnet.html– http://verbs.colorado.edu/~mpalmer/projects/verbnet/downloads.html3/16/2011 CSE842, Spring 2011, MSU 21Proposition Bank (PropBank)• Annotate the Penn TreeBank with predicate-argument information • The semantic roles are defined with respect to an individual verb sense.• Corpus can be used for automatic learning for surface realization of each argument• http://verbs.colorado.edu/~mpalmer/projects/ace.html• Also available under ~cse842/Corpora3/16/2011 CSE842, Spring 2011, MSU 22PropBank• General procedure– Select for each verb the roles that occur most frequently– Use Arg0, Arg1,… Arg5. Arg0 usually stands for Agent, Arg1 for patient or direct object, Arg2 for instrument, indirect object, etc. What each Arg stands for depends on a specific verb sense. 3/16/2011 CSE842, Spring 2011, MSU 23PropBankBUYArg0: buyerArg1: thing boughtArg2: sellerArg3: price paidArg4: benefactiveSELLArg0: sellerArg1: thing boughtArg2: buyerArg3: price paidArg4: benefactivePAYArg0: buyerArg1: price paidArg2: sellerArg3: thing boughtArg4: benefactiveArguments are defined based on each verb3/16/2011 CSE842, Spring 2011, MSU 24Word Senses in PropBankAPPLY“ask


View Full Document

MSU CSE 842 - Natural Language Processing

Course: Cse 842-
Pages: 14
Download Natural Language Processing
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Natural Language Processing and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Natural Language Processing 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?