2005 FX PAL VS

Information about 2005 FX PAL VS

Published on November 1, 2007

Author: Nikita

Source: authorstream.com

Content

Whose presentation is this? SUBJ(present, Violeta Seretan) :  Whose presentation is this? SUBJ(present, Violeta Seretan) OBL(collaborate, Lorenzo Thione) PP-OBJ(with, Lorenzo Thione) SUBJ(supervise, Martin van den Berg) (Decoding the predicate-argument structure of nominalizations) Overview:  Overview nominalization problem NOMLEX resource Denominalizer service based on NOMLEX additional resources (CSLI) APIs for NOMLEX, CSLI related and future work demo Text normalization for QA:  Text normalization for QA Mark Twain published Adventures of Huckleberry Finn in 1885 in America. Who published H.F.? Where was H.F. published? When was H.F. published? QA/NLU needs to deal with a large spectrum of variation in text: morphological: published, publishes syntactic: H.F. was published lexical: {novel, book, masterpiece, work} {publish, write, author, appear} nominalization: the publication Normalization (via parsing): base word form: publishes -> publish; published -> publish canonical word order: SUBJ(publish, Mark Twain); OBJ(publish, H.F.) Lexical semantic resources: synonyms, hyponyms, hypernyms, … What about nominalization? Nominalization:  Nominalization Since the publication of Huckleberry Finn in 1885, there have been many reactions to the novel, some of them quite extreme. When was H.F. published? Nominalization : NP having “a systematic correspondence with a clause structure” (Quirk et al. 1985) Goal: decoding the clause structure Mapping nominal arguments into verbal roles :  Mark Twain’s publication of his book possessive determiner PP adjunct (nominal arguments) the book publication by Mark Twain modifier PP adjunct (nominal arguments) Mark Twain - publish – book SUBJECT OBJECT (verbal roles) Mapping nominal arguments into verbal roles Role ambiguity:  Role ambiguity Rome’s destruction – SUBJ or OBJ? OBJ(destroy, Rome) SUBJ(destroy, Rome) Rome’s destruction by barbarians OBJ Rome’s destruction of Carthage SUBJ Rome’s destruction – OBJ (by default) John’s admiration – SUBJ (by default) NOMLEX – NOMinalization LEXicon:  NOMLEX – NOMinalization LEXicon Macleod et al., New York University 1’025 deverbal nouns detailed mapping from nominal arguments to verb roles :ORTH "destruction" :VERB "destroy" :VERB-SUBC ((NOM-NP :SUBJECT ((N-N-MOD) (DET-POSS) (PP :PVAL ("by"))) :OBJECT ((DET-POSS) (N-N-MOD) (PP :PVAL ("of"))) :REQUIRED ((OBJECT :DET-POSS-ONLY T :N-N-MOD-ONLY T)))) default role role to assign NOMLEXML:  NOMLEXML (NOM :ORTH "accusation" :PLURAL "accusations" :PLURAL-FREQ "not rare" :VERB "accuse" :NOUN-SUBC ((NOUN-PP :PVAL ("about"))) :NOM-TYPE ((VERB-NOM)) :VERB-SUBJ ((DET-POSS) (N-N-MOD) (PP :PVAL ("by"))) :SUBJ-ATTRIBUTE ((COMMUNICATOR)) :OBJ-ATTRIBUTE ((COMMUNICATOR)) :VERB-SUBC ((NOM-NP-PP :SUBJECT ((DET-POSS) (N-N-MOD) (PP :PVAL ("by"))) :OBJECT ((PP :PVAL ("against"))) :PVAL ("of")) (NOM-NP :SUBJECT ((DET-POSS) … Perl NOMLEX API in Java:  NOMLEX API in Java com.fxpal.sake.test (NomLexInterface) com.fxpal.ltng.services.normalization.noun.nomlex (NomLex, NomLexEntry, NomLexClassConstants, Subcat) How useful?:  How useful? Oracle acquired PeopleSoft at the end of last year. Oracle’s acquisition of PeopleSoft at the end of last year… Google hits, 10/25/2005: More hits: Argument-role mapping:  Argument-role mapping Oracle's acquisition of PeopleSoft possessive PP (of ) :ORTH "acquisition" :VERB "acquire" :VERB-SUBC ((NOM-NP :SUBJECT ((DET-POSS) (N-N-MOD) (PP :PVAL ("by"))) :OBJECT ((N-N-MOD) (PP :PVAL ("of")))) Denominalizer:  Denominalizer Input: sentence Output: pairs nominal argument – verb role for each nominalization (noun, (argument –role)*)* Exemples: Oracle's acquisition of PeopleSoft finally materialized after an 18 months struggle between the two companies. (acquisition, (Oracle - SUBJECT) (PeopleSoft - OBJECT)) Oracle acquisition finally materialized. (acquisition, (Oracle - SUBJECT) (Oracle - OBJECT)) Algorithm:  Algorithm parse sentence for each deverbal noun get noun arguments for each NOMLEX entry for noun for each subcat of the entry 1. match arguments against subcat 2. filter assignment results select a subcat output assignments for selected subcat Note: overlapping nominalizations ok: an increase in product sales com.fxpal.ltng.services.normalization.noun.* 1. Matching :  1. Matching Oracle's acquisition of PeopleSoft finally materialized. Arguments (acquisition): POSS(acquisition, Oracle) ADJUNCT(acquisition, of) PP-OBJ(of, PeopleSoft) NOM-NP :SUBJECT ((DET-POSS) (N-N-MOD) (PP :PVAL ("by"))) :OBJECT ((N-N-MOD) (PP :PVAL ("of"))) 2. Filtering:  2. Filtering Oracle's PeopleSoft acquisition finally materialized. Arguments (acquisition): POSS(acquisition, Oracle) MOD(acquisition, PeopleSoft) NOM-NP SUBJECT ((DET-POSS) (N-N-MOD) (PP :PVAL ("by"))) OBJECT ((N-N-MOD) (PP :PVAL ("of"))) Alternatives: Oracle: SUBJECT PeopleSoft: SUBJECT, OBJECT NOMLEX constraints (1):  NOMLEX constraints (1) Uniqueness Constraint: A verbal role may be filled only once. Oracle's PeopleSoft acquisition Matching alternatives: Oracle: SUBJECT PeopleSoft: SUBJECT, OBJECT NOMLEX constraints (2):  NOMLEX constraints (2) Ordering Constraint: If there are multiple pre-nominal arguments, they must appear in the order: SUBJECT, INDIRECT OBJECT, DIRECT OBJECT, OBLIQUE. FX’s printer sales grew by 50%. Matching alternatives: FX: SUBJECT, OBJECT printer: SUBJECT, OBJECT order: FX, printer verbal roles: SUBJECT, OBJECT NOMLEX constraints (3):  NOMLEX constraints (3) Obligatoriness Constraint: By default, the subject and object are optional. A NOMLEX entry can specify obligatory roles to be filled. circulation - REQUIRED (SUBJECT) blood circulation SUBJ(circulate, blood) destruction - REQUIRED ((OBJECT :DET-POSS-ONLY T :N-N-MOD-ONLY T)))) Rome’s destruction OBJ(destroy, Rome) Selectional Restrictions :  Selectional Restrictions com.fxpal.ltng.services.normalization.noun.csli (Nouns, Verbs, NounsVerbs) Applying selectional restrictions:  Applying selectional restrictions room reservation Alternatives: room - SUBJECT, OBJECT reserve - selectional restrictions: SUBJECT: sentient; OBJECT: * room - location, physobj semantic types for about 5000 N selectional restrictions for about 5000 V 459/941 verbs from NOMLEX (48.77%) Coverage extension:  Coverage extension What if a noun is not in NOMLEX? additional deverbal nouns in the CSLI data 4’087 “event nouns” 3348 new, 739 already in NOMLEX 3348/1025 326% more data NOMLEX template: NOM-NP :SUBJECT ((DET-POSS) (N-N-MOD) (PP :PVAL ("by"))) :OBJECT ((DET-POSS) (N-N-MOD) (PP :PVAL ("of"))) Future work:  Future work extensive test and evaluation other nominalization data deverbal noun recognition mapping information (FrameNet) other lexical resources PropBank – semantic roles VerbLex – selectional restrictions role assignment in context word sense disambiguation, anaphora, discourse collocations the author will make no accusation SUBJ(make, author) -> SUBJ (accuse, author) Related work:  Related work PUNDIT system (Dahl et al., 1987) SNOWY QA system (Hull and Gomez 1996) NOMLEX for IE (Meyers et al., 1998) N-N interpretation (Lapata 2002, Girju et al. 2004) References:  Dahl, Deborah A., Palmer, Martha S.; and Passonneau, Rebecca J. 1987. "Nominalizations in PUNDIT." Proceedings of the 25th Annual Meeting of the Association for Computational Linguistics, Stanford, CA. Girju, Roxana, Ana-Maria Giuglea, Marian Olteanu, Ovidiu Fortu, Orest Bolohan, and Dan Moldovan. Support vector machines applied to the classification of semantic relations in nominalized noun phrases. In Proceedings of the HLT-NAACL Workshop on Computational Lexical Semantics, 2004. Hull, Richard and Fernando Gomez (1996). Semantic Interpretation of Nominalizations. PDF Format. Proceedings of the Thirteenth National Conference on Artificial Intelligence, Portland, Oregon, August, 1996, pp. 1062-8. Lapata, Maria. 2002. The Disambiguation of Nominalisations. Computational Linguistics 28:3, 357-388. Macleod, Catherine, Ralph Grishman, Adam Meyers, Leslie Barrett, and Ruth Reeves. 1998. Nomlex: A lexicon of nominalizations. In Proceedings of the 8th International Congress of the European Association for Lexicography, pages 187–193, Liège, Belgium. Meyers A., et al. Using NOMLEX to produce nominalization patterns for information extraction. In Proceedings of the COLING-ACL Workshop on Computational Treatment of Nominals, 1998. Quirk, S. R., Greenbaum, G. Leech, and J. Svartvik. 1985. A comprehensive grammar of English language, Longman, Harlow. Terada Akira, Tokunaga Takenobu. Corpus based method of transforming nominalized phrases into clauses for text mining application. IEICE Transactions on Information and Systems. Vol.E86-D. No.9. pp.1736 -- 1744. 2003. References Slide25:  Thank you! Selectional restrictions data:  Selectional restrictions data CSLI resource: nouns 4447 semantic types (ontology) verbs 4858 subcategorizations selectional restrictions noun-verb 5700 V (9415 N) noun-verb pairs Grammatical Transfer:  Grammatical Transfer FrameNet:  FrameNet aim: word – semantico-syntactic mapping semantic roles: frame elements (frame-specific) BNC corpus (100M words); American English – LDC, ANC more than 600 frames, about 9.000 words Example: accusation frame: Judgment_communication FE (for this word) and their realization: NOMLEX constraints (4):  NOMLEX constraints (4) restrictions on possible combinations specified in NOMLEX entry adaptation :NOT ((AND :SUBJECT ((DET-POSS) (N-N-MOD)) :OBJECT ((N-N-MOD)) *plants' weather adaptation plants’ adaptation to weather Note: Not implemented (cannot decide which assignment to remove). Denominalizer UI:  Denominalizer UI parse triples output com.fxpal.sake.test.DenominalizerTest

Related presentations


Other presentations created by Nikita

Modems
28. 11. 2007
0 views

Modems

Intro to CMMI
02. 10. 2007
0 views

Intro to CMMI

Mantsch Mazur Tank Insulation
06. 11. 2007
0 views

Mantsch Mazur Tank Insulation

embrapa2
27. 11. 2007
0 views

embrapa2

G050249 00
28. 11. 2007
0 views

G050249 00

csw06 lord
25. 10. 2007
0 views

csw06 lord

AboutCaravaggio
31. 10. 2007
0 views

AboutCaravaggio

THE RENAISSANCE
31. 10. 2007
0 views

THE RENAISSANCE

HeWhoLaughs LastsPlenary
02. 11. 2007
0 views

HeWhoLaughs LastsPlenary

JavaScript UE1
05. 11. 2007
0 views

JavaScript UE1

buchner
05. 11. 2007
0 views

buchner

6 3 Ship Framing System
06. 11. 2007
0 views

6 3 Ship Framing System

NOROVIRUSESpres
07. 11. 2007
0 views

NOROVIRUSESpres

Volkswagen Stiftung
14. 11. 2007
0 views

Volkswagen Stiftung

Trigonometry examples
15. 11. 2007
0 views

Trigonometry examples

Lufthansa
16. 11. 2007
0 views

Lufthansa

pipeline to the pros updated
20. 11. 2007
0 views

pipeline to the pros updated

tango in a nutshell
22. 11. 2007
0 views

tango in a nutshell

en what is turtle f2f
19. 12. 2007
0 views

en what is turtle f2f

Qatar 2005
28. 12. 2007
0 views

Qatar 2005

butterflydance
23. 11. 2007
0 views

butterflydance

H3NPSmall
02. 01. 2008
0 views

H3NPSmall

nano5
02. 01. 2008
0 views

nano5

flex components slides
28. 11. 2007
0 views

flex components slides

jmcmorrow
06. 12. 2007
0 views

jmcmorrow

fishing
07. 01. 2008
0 views

fishing

Dormancy
07. 01. 2008
0 views

Dormancy

TE Tutorial ACL07
31. 10. 2007
0 views

TE Tutorial ACL07

Knots A
25. 10. 2007
0 views

Knots A

Tutorial AOD 100305
29. 10. 2007
0 views

Tutorial AOD 100305

38006461
21. 11. 2007
0 views

38006461

helioseismology
14. 11. 2007
0 views

helioseismology

Knoblock p123
15. 11. 2007
0 views

Knoblock p123

Lt2 BusiPortfoAnalysis
20. 02. 2008
0 views

Lt2 BusiPortfoAnalysis

Guidaversione19 0SistemaDRG
30. 10. 2007
0 views

Guidaversione19 0SistemaDRG

Modern Ideas
24. 02. 2008
0 views

Modern Ideas

Lotrel and Diovan Talk
05. 03. 2008
0 views

Lotrel and Diovan Talk

BusinessBuddyPresent ation
03. 10. 2007
0 views

BusinessBuddyPresent ation

DFASColumbusConferen ce
01. 11. 2007
0 views

DFASColumbusConferen ce

student movement
25. 12. 2007
0 views

student movement

elettivo2006
04. 12. 2007
0 views

elettivo2006

akshaya friends
21. 12. 2007
0 views

akshaya friends

lctpcremarks
27. 03. 2008
0 views

lctpcremarks

AUTNZFuturesDWYER
30. 03. 2008
0 views

AUTNZFuturesDWYER

Lecture24 07
09. 10. 2007
0 views

Lecture24 07

Lesko Homestake Minn
05. 12. 2007
0 views

Lesko Homestake Minn

Deadlock 1941
13. 11. 2007
0 views

Deadlock 1941

20070615 POLICY grid
24. 12. 2007
0 views

20070615 POLICY grid

NYU Brownbag
06. 11. 2007
0 views

NYU Brownbag

Meow
05. 11. 2007
0 views

Meow

ahm2004 workflow
14. 12. 2007
0 views

ahm2004 workflow

08Tirpak
07. 11. 2007
0 views

08Tirpak

UNFFOlgas website
26. 11. 2007
0 views

UNFFOlgas website

rtd Jul24 03
30. 11. 2007
0 views

rtd Jul24 03

Princeton Oct05
05. 11. 2007
0 views

Princeton Oct05