(Words and their meaning) 1
Close synonymy Small/little I have little/*small money. This is Fred, my big/*large brother. Animacy My neighbor admires my garden. *My car admires my garden. Bill frightened his dog/*hacksaw. 2
This is yellow. This is a pencil.?this is a yellow pencil. This is big. This is a whale.?this is a big whale. Lee kissed Kim passionately.?lee kissed Kim.?Kim was kissed.?lee touched Kim with her lips.?lee married Kim.?Kim kissed Lee.?Lee kissed Kim many times. 3
Fuzziness (rich, tall, green, clean) Typicality, prototypes Bird: robin vs. penguin Lexicalization (snow) (glint, glimmer, glitter, gleam, glisten, glow, glare) Inventories 4
Culture-specific concepts L1 concept not lexicalized in L2 L1 word is semantically complex Different L1/L2 meaning distinctions L1/L2 lacks a hypernym/hyponym 5
Ecology (flora, fauna: tundra, taiga ) Material culture (food, clothes, transport) Social culture (work, leisure) Organizations, customs, concepts (political, religious, artistic) Gestures and habits 6
The way basic underlying concepts are lexically realized in a language Wide variation crosslinguistically English: motion (V) + path (PP) vs. Romance languages He swam across the river. Il traversa la fleuve à la nage L1 verb L2 prepositional phrase L1 preposition L2 verb 7
flimped : kissed someone who is allergic to John flimped garlic. 8
I am firm. You are obstinate. He is a pig-headed fool. Fairer sex, female, broad Between jobs, out of work, on the dole 9
Verb complement: infinitive -> noun I m waiting for the postman to come. J attends l arrivée du facteur. A proposal to pay for the equipment Une proposition de paiement du matériel 10
Non-compositional collocations Severe lexical constraints Vary crosslinguistically Off his rocker/#rocking chair Gnashing of teeth/#molars Shot herself in the foot/#toe 11
Ways of representing concepts Basic entities, actions Relationships between them Compositionality of meaning Some are very formal, some very informal Various linguistic theories might involve different representations 12
Measuring how near words, collocations, words, phrases, sentences, documents are in meaning Classes, domains, hierarchical arrangement play crucial role 13
Function of constituents Assignment Verbs assign theta-roles to arguments Prepositions assign theta-roles to objects Deep structure position: determines thematic role 14
Role played by each NP in a sentence Agent: entity that performs an action Theme, Patient: entity that undergoes an action Source, Goal, Location, Instrument Experiencer: perceiver of a cognitive stimulus Stimulus: perceived cognitive stimulus 15
The dog chased the cat up the hill. Agent <Ag,Th,Loc> Theme Location 16
Grammatical realization of semantic features 17
Different types of lexical ambiguity Polysemy: 2+ related senses (bright, deposit) Homonymy: 2+ unrelated senses (bat, file) Won t address other kinds today Lexical ambiguity is rampant in English Average # senses: 4.74 for nouns, 8.63 for verbs Many words overlap both categories Lexical ambiguity is: dangerous? helpful? immaterial? Contributes to language processing difficulty, complexity Contributes to vagueness, underspecification 18
Disambiguation: figuring out which sense is being used in a given instance/context It s clear humans need to do (some) WSD How much? How? Do computers need to do (some) WSD? How much? How? Is it even possible? Not an end in itself, but crucial to other tasks Many applications: MT, IR, content analysis, grammatical analysis, speech, spelling/grammar checkers, etc. What are the techniques? How (well) do they work? How can they be evaluated? 19
Iraqi head seeks arms William Kelly was fed secretary Police begin push to run down jaywalkers Dealers will hear car talk at noon Red tape holds up new bridges Kids make nutritious snacks Lansing residents can drop off trees Farmer Bill Dies in House 20
21
Translation: SL/TL granularity mismatches wall Mauer/Wand; river fleuve/rivière Erroneous translations Ladies may have a fit upstairs. (in a Hong Kong tailor shop) Erroneous L2 usage 22
Large-scale English coverage > 152,000 words Many, many lexical relations (paradigmatic, syncategorematic, frequency-ranked) Subcategorization information Definitions, glosses, usage examples Machine-readable, widely used in NLP Free, web-enabled, downloadable Developed by Princeton s CogSci lab 23
1 Something ----s 2 Somebody ----s 20 Somebody ----s somebody PP 3 It is ----ing 21 Somebody ----s something PP 4 Something is ----ing PP 22 Somebody ----s PP 5 Something ----s something Adjective/Noun 23 Somebody's (body part) ----s 6 Something ----s Adjective/Noun 24 Somebody ----s somebody to INFINITIVE 7 Somebody ----s Adjective 25 Somebody ----s somebody INFINITIVE 8 Somebody ----s something 26 Somebody ----s that CLAUSE 9 Somebody ----s somebody 27 Somebody ----s to somebody 10 Something ----s somebody 28 Somebody ----s to INFINITIVE 11 Something ----s something 29 Somebody ----s whether INFINITIVE 12 Something ----s to somebody 30 Somebody ----s somebody into V-ing 13 Somebody ----s on something something 14 Somebody ----s somebody something 31 Somebody ----s something with something 15 Somebody ----s something to somebody 32 Somebody ----s INFINITIVE 16 Somebody ----s something from somebody 33 Somebody ----s VERB-ing 17 Somebody ----s somebody with something 34 It ----s that CLAUSE 18 Somebody ----s somebody of something 35 Something ----s INFINITIVE 19 Somebody ----s something on somebody 24
Sample sentence: Dogs chew leashes. dogs: N[pl], V[3sg] chew: N[sg], V[~3sg] leashes: N[pl], V[3sg] dogs: n-animal, n-artifact, n-person, v-motion chew: n-act, v-consumpt, n-food leashes: n-artifact, v-contact, n-quantity 25
26 Noun classes (noun.tops) noun.act noun.animal noun.artifact noun.attribute noun.body noun.cognition noun.communication noun.event noun.feeling noun.food noun.location noun.group noun.motive noun.object noun.person noun.phenomenon noun.plant noun.possession noun.process noun.quantity noun.relation noun.shape noun.state noun.substance noun.time 15 Verb classes verb.body verb.change verb.cognition verb.communication verb.competition verb.consumption verb.contact verb.creation verb.emotion verb.motion verb.perception verb.possession verb.social verb.stative verb.weather 26
The noun "dog" has 7 senses in WordNet. 1. dog, domestic animal, Canis familiaris -- ("the dog barked all night") 2. frump, dog -- (dull unattractive unpleasant female; "she's a real dog") 3. dog -- (informal term for a man; "you lucky dog") 4. cad, bounder, dog -- (someone morally reprehensible; "you dirty dog") 5. frank, frankfurter, hotdog, hot dog, dog, wiener, wienerwurst, weenie -- (a smooth-textured sausage of minced beef or pork usually smoked; often served on a bread roll) 6. pawl, detent, click, dog -- (a hinged catch that fits into a notch of a ratchet to move a wheel forward or prevent it from moving backward) 7. andiron, firedog, dog, dog-iron -- (metal supports for logs in a fireplace; "the andirons were too hot to touch") The verb "dog" has 1 sense in WordNet. 1. chase, chase after, trail, tail, tag, give chase, dog, go after, track -- (go after with the intent to catch) 27
28
...... Sense 4 cad, bounder, blackguard, dog, hound, heel -- (someone who is morally reprehensible) => villain, scoundrel -- (a wicked or evil person; someone who does evil deliberately) => unwelcome person, persona non grata -- (a person who for some reason is not wanted or welcome) => person, individual, someone, somebody, mortal, human, soul -- (a human being) => organism, being -- (a living thing that has (or can develop) the ability to act or function independently) => living thing, animate thing -- (a living (or once living) entity) => object, physical object -- (a tangible and visible entity; an entity that can cast a shadow) => entity -- (that which is perceived or known or inferred to have its own distinct existence (living or nonliving)) => causal agent, cause, causal agency -- (any entity that causes events to happen) => entity -- (that which is perceived or known or inferred to have its own distinct existence (living or nonliving)) Sense 5 frank, frankfurter, hotdog, hot dog, dog, wiener, wienerwurst, weenie -- (a smoothtextured sausage of minced beef or pork usually smoked; often served on a bread roll) => sausage -- (highly seasoned minced meat stuffed in casings) => meat -- (the flesh of animals (including fishes and birds and snails) used as food) => food -- (any solid substance (as opposed to liquid) that is used as a source of nourishment) => solid -- (a substance that is solid at room temperature and pressure) => substance, matter -- (that which has mass and occupies space) => entity -- (that which is perceived or known or inferred to have its own distinct existence (living or nonliving)) Sense 6 pawl, detent, click, dog -- (a hinged catch that fits into a notch of a ratchet to move a wheel forward or prevent it from moving backward) => catch, stop -- (a restraint that checks the motion of something) => restraint, constraint -- (a device that retards something's motion) => device -- (an instrumentality invented for a particular purpose) => instrumentality, instrumentation -- (an artifact (or system of artifacts) that is instrumental in accomplishing some end) => artifact, artefact -- (a man-made object taken as a whole) => object, physical object -- (a tangible and visible entity; an entity that can cast a shadow) => entity -- (that which is perceived or known or inferred to have its own distinct existence (living or nonliving)) => whole, whole thing, unit -- (an assemblage of parts that is regarded as a single entity) => object, physical object -- (a tangible and visible entity; an entity that can cast a shadow) => entity -- (that which is perceived or known or inferred to have its own distinct existence (living or nonliving)) 29
WordNet online www.visualthesaurus.com Lots of others 30
WS annotation is an expert task, not a natural task for native speakers Inter-annotator agreement among experts: 90% when limited to two senses; 70% when 8 or more senses involved Much less for untrained annotators Trained lexicographers approach task differently than normal people (wider array of strategies) Time-consuming, costly, fairly tedious 31
stative verb: social verb: contact verb: consumption verb: competition verb: 32
stative verb meanings: 1. function 3. effectuate, bring about 8. promote, benefit 9. serve, do, spend, pass 12. suffice, do, answer, serve, satisfy, fulfill social verb meanings: 2. do duty in a specific function 4. be used by, as a utility 7. serve 10. attend to, assist 13. do military service contact verb meanings: 11. serve, process, swear out 14. breed consumption verb meanings: 5. help with food or drink 6. serve up, dish out, dish up competition verb meaning: 15. put the ball into play 33
stative verb meanings: 1. function:...i think it will serve a purpose... 3. effectuate, bring about:...they had only served to confirm my faith... 8. promote, benefit:...the stickiness of the berry served to attach it to the tree... 9. serve, do, spend, pass:...i served a mission... 12. suffice, do, answer, serve, satisfy, fulfill:...it may serve other purposes... social verb meanings: 2. do duty in a specific function:... serve as a visiting teacher... 4. be used by, as a utility:...this tabernacle has served us well... 7. serve:...the opportunity we have had of serving the Church... 10. attend to, assist: God help us all to serve one another... 13. do military service: We have young men serving in the military... contact verb meanings: 11. serve, process, swear out: People go around serving notice... 14. breed (N/A) consumption verb meanings: 5. help with food or drink:...we had been served our breakfast... 6. serve up, dish out, dish up:...the wild music that is served up... competition verb meaning: 15. put the ball into play:...in tennis if we didn t serve well... 34
350 300 250 200 150 100 50 0 GosFu n GConf BoM WSJ Xerox EUmtg GosPr n JSPam 59 223 115 105 60 294 104 103 35