1、A Computational View of Verb Predicates and Semantic Roles,Fernando Gomez School of Computer Science University of Central Florida Orlando, Fl 32816 gomezcs.ucf.edu www.cs.ucf.edu/gomez,Description of the Problem,Design and implement a program that takes as input any English sentence and, for every
2、clause in the sentence, Determines the verb meaning, the semantic roles, adjuncts, attach PPs, solves the senses of many nouns in the sentence, and also resolves deverbal nominalizations.,The Role of WordNet,WordNet provides two major resources for defining the predicates:a) A General Ontology for E
3、nglish NounsUsed in the selectional restrictions of the predicatesb) A Classification of English Verb into ClassesUsed in identifying generic predicates whose definitions would apply to many verbs under that class,An example of WordNet Verb Class: travel,Sense 1 travel, go, move, locomote - (change
4、location; move, travel, or proceed)= go around, spread, circulate - (of information)= carry - (cover a certain distance or advance beyond, as of a ball in golf; “The drive carried to the green“)= ease - (move gently or carefully; “He eased himself into the chair“)= whish - (move with a whish)= seek
5、- (go to or towards; “a liquid seeks its own level“)= whine - (move with a whining sound; “The bullets were whining past us“)= fly - (be dissipated; “Rumors and accusations are flying“)= ride - (move like a floating object; “The moon rode high in the night sky“)= come - (cover a certain distance: “S
6、he came a long way“)= ghost - (move like a ghost; “The masked men ghosted across the moonlit yard“)= travel - (undergo transportation, as in a vehicle)= fly - (travel in an airplane; “she is flying to Cincinnati tonight“; “Are we driving or flying?“)= hop - (informal: travel by means of an aircraft,
7、 bus, etc.; “She hopped a train to Chicago“; “He hopped rides all over the country“)= ride - (be carried or travel on or in a vehicle; “I ride to work in a bus“; “He rides the subway downtown every day“)= chariot - (ride in a chariot)= bicycle, cycle, bike, pedal, wheel - (ride a bicycle)= backpedal
8、 - (pedal backwards, as on a bicycle)= motorcycle, cycle - (ride a motorcycle),The Syntax of Roles,(role ( () () . () ()wherestands for any Semantic Rolestands for one or more Selectional Restrictionsandstands for one or more Grammatical Relations/Syntactic RelationsExample: (to-loc(location) (obj)(
9、physical-thing) (prep to),Examples of Grammatical Relations,Subj: Subject of verbObj: First Postverbal NPObj2: Second Postverbal NPSubj-if-obj: Subject of a verb that has also an objPrep: PP,Examples of Grammatical Relations,CP: Any Complement PhraseCP-S: VP_S clauseCP-INF: VP_infCP_ING: VP_ingPREP-
10、CP: CP clause introduced by a preposition,A Generic Predicate: Communicate,COMMUNICATE(IS-A (INTERACT)(WN-MAP (COMMUNICATE2)(AGENT (HUMAN-AGENT ANIMAL ) (SUBJ)(THEME (COMMUNICATION (POSSESSION PHYSICAL-THING STATE-R) THING) (CP OBJ OBJ2) (COMMUNICATION THING) (PREP ABOUT OF)(COMMUNICATION ABSTRACTIO
11、N) (PREP ON) (RECIPIENT (HUMAN-AGENT ANIMAL) (OBJ (PREP WITH TO)(FORM-OR-MEDIUM-OF-EXPRESSION(WRITTEN-COMMUNICATION SPEECH-ACT CREATION) (SUBJ (PREP IN),“She briefed the president.“,(Clause CL11(SUBJ : (PRON SHE) (PERSON SHE) )(VERB : BRIEF )(OBJ : (DFART THE) (NOUN PRESIDENT) (LEADER PRESIDENT1 PRE
12、SIDENT2 PRESIDENT3 PRESIDENT4PRESIDENT5) )TRANS-INFORCOMMUNICATEINTERACTACTIONROOT,Criteria for creating subpredicates,The differentia between a predicate and its subpredicates are given by one or more of the following:Different selectional restrictions for the semantic rolesDifferent syntactic rela
13、tions for the semantic rolesSpecific sets of inferences associated with the subpredicates,Definitions for Some Small Classes of Communicate2,ADVISE(IS-A(COMMUNICATE)(WN-MAP(ADVISE1)(THEME(THING) (CP (PREP ABOUT)(PHYSICAL-THING) THING) (PREP ON) (RECIPIENT(HUMAN-AGENT ANIMAL) (OBJ)SMILE(IS-A(GRIMACE)
14、(WN-MAP(SMILE1) (RECIPIENT(HUMAN-AGENT ANIMAL) (PREP AT TO) (THEME(NIL)(NIL),Something We Missed,The senator advised against the war.The doctor advised complete rest.Please advise me of the cost.,A Small Verb Subclass,Sense 1 smile - (change ones facial expression by spreading the lips, often to sig
15、nal pleasure)= dimple - (produce dimples while smiling; “The child dimpled up to the adults“)= grin - (to draw back the lips and reveal the teeth, in a smile, grimace, or snarl)= beam - (smile radiantly; express joy through ones facial expression)= smirk, simper - (smile affectedly or derisively)= s
16、neer - (smile contemptuously),A Subpredicate of Transfer of Information,MISINFORM (MISINFORM1)HIDE-INFORMATIONCONCEAL-INFORMATION (CONCEAL2)COVER-HIDE-INFORMATIONCOVER-UP-MISINFORMSWEEP-UNDER-THE-RUGLIE-TO-SOMEBODY (LIE5)EXAGGERATE (OVERSTATE1)BLOW-EXAGGERATETWIST-CHANGE-THE-MEANING (TWIST8)CONTORT-
17、DISTORT (CONTORT?),A Subpredicate of Transfer of Information,TEACH (TEACH1)HAMMER-IN (HAMMER_IN1)HAMMER-TEACHLECTURE (LECTURE1)EDUCATE (EDUCATE1 TRAIN2 EDUCATE3)BRING-UP (REAR2)TRAIN-SOMEBODY (TRAIN1 TRAIN2)CULTIVATE-KNOWLEDGE-WISDOM (CULTIVATE3)EDUCATE-PEOPLEPREPARE-SOMEBODY-FOR-SCHOOLINDOCTRINATE
18、(INDOCTRINATE1)INFECT-INDOCTRINATEPOISON-INDOCTRINATETRAIN-ANIMAL (TRAIN1)IMPRESS-ON-SOMEONEINSTILL-PUT-IDEASINSTRUCT-TEACHSHOW-TEACH,A Subpredicate of Transfer of Information,CRITICIZE (CRITICIZE1)DISPARAGE (DISPARAGE1)ATTACK-VERBALLY (ATTACK2)CURSE-BLASPHEME (CURSE1 CURSE2)SWEAR-BLASPHEMVILIFY-VIT
19、UPERATE (VILIFY1)REBUKE (REBUKE1)CHASTIZE (CHASTIZE1)DENOUNCE (DENOUNCE1 DENOUNCE3 DENOUNCE4)CONDEMN-DENOUNCEPICK-ON-CRITICIZETEAR-APART-CRITICIZE,Semantic Roles and Predicate Classes,Semantic Roles Depend on the Generic Predicate for Each Predicate ClassThe Generic Predicate Determines the Meaning
20、and Number of the Semantic Roles (Gomez, 1998),Examples of Generic Predicate Classes,Change-Location (Agent, To-Loc, From-Loc, Distance, Instrument, At-Speed) Cause-to-Change-Location (Agent, Theme, Source, Goal, Inanimate-Cause, Instrument) Transfer-of-Possession (Agent, Theme, From-Poss, To-Poss)
21、Cause-Change-of-State (Agent, Theme, Beginning-State, Ending-State,Inanimate-cause) Prevent (Agent, Theme, Event-Prevented, Recipient, Inanimate-Cause) Judge (Agent, Theme, Recipient) Permit (Agent, Theme, Recipient, Inanimate-Cause),Hierarchy of Semantic Roles,from-person = beginning-state (BREAK-O
22、FF-FROM-SOMEBODY)in-court-tribunal = at-loc (CHALLENGE-SOMETHING)event-prevented = theme (PREVENT)at-inquiry-investigation = at-activity (CLEAR-SOMEBODY-OF-BLAME-GUILT)cure-agent = inanimate-cause (CURE-A-DISEASE)work-place = at-loc (DO-SERVICE)from-organization-or-activity = beginning-state (RETIRE
23、-FROM-AN-ACTIVITY),Semantic Interpretation Algorithm,The interpretation algorithm is activated after a sentence is parsed.The parser does not resolve structural ambiguity.The determination of verb meaning and semantic roles is interdependent.A predicate explains a syntactic relation if it has a sema
24、ntic role realized by that syntactic relation.The predicate that has the most semantic roles realized is selected as the meaning of the verb.,Illustration of the Algorithm,P1: leave-a-place P2: leave-an-organizationP3: abandon-somebodyP4: leave-a-vehicle leave P5: leave-behindP6: leave-give . .Pi Sh
25、e left for Texas on a plane. She left a fortune to her daughter. He left Texas. She left school. He left with his friends.,Problems with the WordNet Verb Classes as Relate to Predicates,Verb forms within a class may realize their semantic roles by different:a) Syntactic Relations and/orb) Selectiona
26、l Restrictions,Problems with the selectional restrictions,Sense 1 reach, attain, make, hit, arrive at, gain - (reach a destination, eitherreal or abstract; “We hit Detroit by noon“; “The water reached the doorstep“;= catch up - (reach a the point where one should be after a delay; “I caught up on my
27、 homework“)= come back - (even the score, in sports)= scale, surmount - (reach the highest point of; “We scaled the Mont Blanc“)= breast - (reach the summit: “They breasted the mountain“)= access, get at - (reach or gain access to)= peak, reach a peak - (to reach the highest point; attain maximum in
28、tensity, activity: “That wild, speculative spirit peaked in 1929.“)= crest - (reach a high point; “The river crested last night“)= bottom out - (reach the low point)= make - (reach in time; “We barely made the plane“),Problem with the Syntactic Relations,Sense 1 accuse, impeach, incriminate, crimina
29、te - (bring an accusation against; level a charge against; “He charged the man with spousal abuse“)= reproach, upbraid - (utter a reproach to; “The president reproached the general for his irresponsible behavior“)= arraign - (accuse of a wrong or an inadequacy)= impeach - (charge with a crime or mis
30、demeanor)= recriminate - (return an accusation against someone or engage in mutual accusations; charge in return)= charge, lodge, file - (file a formal charge against; “The suspect was charged with murdering his wife“)= impeach - (charge with an offense or misdemeanor; “The public officials were imp
31、eached“),Defining Predicates for Individual Verbs with High Polysemy,The definition is identical as for defining predicates for verb classes.However,The order in which the predicates are defined is relevant because the algorithm prefers them in the order in which they are defined.,An Example of Pred
32、icates for an Individual Verb,ADDRESS(ADDRESS-AN-ENVELOPE(IS-A(LABEL-SOMETHING) ;(WN-MAP(ADDRESS3)(THEME(ENVELOPE1)(OBJ)(THEMATIC-RULE(REQUIRE(THEME )(ADDRESS-SOMEONE(IS-A(SPEAK-TO-SOMEBODY) ; (WN-MAP(ADDRESS1)(ADDRESS2)(AGENT(HUMAN-AGENT ANIMAL)(SUBJ)(RECIPIENT(HUMAN-AGENT ANIMAL)(OBJ),A new addres
33、s,(ADDRESS-A-PROBLEM-TASK-SITUATION(WN-MAP(ADDRESS6);?(IS-A(DEAL-WITH-A-PROBLEM-TASK-SITUATION)(THEME(DIFFICULTY2 DIFFICULT3 CHALLENGE1 ACTION )(OBJ) ; SHE ADDRESSED MANY IMPORTANT TOPICS IN HER BOOK.(ADDRESS-DISCUSS(IS-A(DISCUSS-ABOUT) ; (WN-MAP(ADDRESS7)(THEME(HUMAN-AGENT) THING) (OBJ),An Example
34、of Predicates for an Individual Verb,(ADDRESS-A-SPEECH-WRITTEN-COMMUNICATION-TO-SOMEBODY(IS-A(TRANS-INFOR) ;(WN-MAP(ADDRESS5) ? (AGENT(HUMAN-AGENT ANIMAL)(SUBJ-IF-OBJ)(THEME(COMMUNICATION)(OBJ)(THEMATIC-RULE(REQUIRE(THEME ) ;ALL ICELANDERS ARE ADDRESSED BY THEIR FIRST NAMES.(ADDRESS-GREET-SOMEONE(IS
35、-A(NAME-SOMETHING)(WN-MAP(ADDRESS4)(RECIPIENT(HUMAN)(OBJ)(NAME-OF(LANGUAGE_UNIT1)(PREP BY AS)(PERSON) (PREP AS) ),Grounding the Ontology on the Semantic Interpretation Algorithm (Gomez, 2001, 2003),The role of the ontology is essential because if the ontological categories are wrong, the selectional
36、 restrictions in the predicates will be also wrong.We did not proceed by looking into the upper-level ontology to find out which categories may require changes. But,The testing of the predicates determined for us which ontological categories may require changes.,Illustrations of Ontological Changes,
37、Define Selectional Restriction for hide 2 in WN. The fish hides in a crevice.Define Selectional Restrictions for burn 1 in WN. She burned the letter.Define Selectional Restrictions for flow 2 in WN. Blood flowed from the wound.,Status of the Work,We have mapped 95% of WN verb classes into predicates
38、.We have defined over 3000 predicates.,Panorama of the Upper-level Ontology of Predicates,Cause-change-of-state (609 subpredicates) cause-change-of-state-of-animal-being (140) arouse-feelings-emotions (52) cause-to-act (19) injure-hurt-somebody-or-oneself (18) increase (31) improve (19) worsen (10)
39、terminate (16) physical-change-of-state (14) solidify liquefy cause-change-of-integrity (22), transform (9) and others.,Cause-to-Change-Location,Cause-to-change-location (379) put (75) remove (53) transport (23) propel (20) connect (22) flow (12) pull (9) push (9)send (9),Change-Location and Interac
40、t,Change-Location (238) walk (14) hike march sneak-walk enter (10) leave-a-place (11) arrive-to-a-place (10)Interact (372) communicate (243) treat-an-animal-or-human (26) treat-unjustly-somebody (9) behave (9) join-a-group-or-a-human (9),Transfer of Something and Make-Or-Create-Something,Transfer-of
41、-something (293) transfer-of-possession (231) give (31) get (132)Make-or-create-something (144) initiate-something (30) create-art (28) produce (10) prepare-something (10),Judge,Judge (182) pass-a-negative-judgment-on (36) disapprove oppose-ideas oppose-people put-value-to-something (12) praise (7)
42、accept-admit-a-fact (30) confirm-corroborate (11) deny-something-to-somebody (14) accuse (11),Experience, Think and Decide,Experience (110) feel-a-state-or-emotions (25) perceive (21) like-something (36) experience-event-state-abstraction (11)Think (115) analyze (31) plan (13) reason-conclude (9) as
43、sociate (7)Decide (92) exert-control-over (65) restrain (22) manage (23),Touch and Spend-Something,Touch (55) handle-operate (18) hit-something (24)Spend-Something (52) ingest (31) Eat,Other Unique Predicate Classes,Prevent (45) Move-body-position (33) Know (31) Fail-to-do-something (33) Fight (31)
44、Expel-substance-from-the-body (23) Do-act (27) Appoint-somebody (15) Allow-something (21) Support-something (24) Succeed (23) Utilize (11) Stative-Predicates (223) be-at-a-place include,Testing of the Predicates,We have tested 400 verbs and produced a small corpus of 500 interpreted sentences from T
45、he World Book Encyclopedia, (WorldBook, Inc. Chicago). (This corpus is available in my homepage)For verbs having 10 senses or more, the algorithm selected correctly the meaning of the verb in 85% of the cases.For verbs having less than 10 senses, the algorithm selected the correct sense of the verb
46、in 92% of the cases.If the predicate is selected correctly, the semantic roles are correctly determined 97% of the cases.,Conclusions,We have presented methods in lexical semantic to define predicates for English verbs.The method uses WordNet noun ontology for the selectional restrictions in the sem
47、antic roles of the predicates, andIt also uses WordNet verb classes to define generic predicates that apply to a large class of verbs.We have provided definitions for over 3000 predicates, and mapped 95% of WordNet verb classes into predicates.,Conclusions (continuation),An algorithm that uses the p
48、redicate definitions has been designed and implemented.The algorithm is used to test and refine the definition of the predicates.The algorithm has provided essential information to reorganize the upper-level ontology of WordNet.By using the algorithm and the predicates, we have given some steps to a
49、utomatically produce semantic tagged corpora.,Some References C. Fellbaum (1998) “A Semantic Net of English Verbs“ In WordNet: An electronic Lexical Database and some of its applications, Fellbaum, C. (editor) MIT Press, 1998.F. Gomez (1998) “Linking WordNet Verb Classes to Semantic Interpretation,“
50、 In the COLING-ACL Workshop on Usage of WordNet in NLP, U. of Montreal.F. Gomez (2001) “An Algorithm for Aspects of Semantic Interpretation Using an Enhanced WordNet,“ In 2nd Meeting of the North American Chapter of the Association for Computational Linguistics, NAACL-2001, CMU.F. Gomez (2001) “Grou
51、nding the Ontology on the Semantic Interpretation Algorithm“, CS-TR-01-01, Feb-2001. Also to appear in the 2nd International Conference in WordNet, Jan-04G. Miller (1998) “Nouns in WordNet,“ in WordNet: An electronic Lexical Database and some of its applications“, Fellbaum, C. (editor) MIT Press, 19
52、98.Levin, B. English Verb Classes and Alternations: A Preliminary Investigation University of Chicago Press, 1993, Chicago.Pinker, S. Learnability and Cognition, MIT Press, 1989, Cambridge, Mass.Pritchett, B. L. Grammatical Competence and Parsing Performance, The University of Chicago Press“, 1992. Chicago,Illinois.Grimshaw, J. Argument Structure, MIT Press, 1990, Cambridge, Mass.,
