ognitiongedr) CDC JHU ACE2005 CDC ACE2005 IBM CDC ACE2005 CDC 1 ACE [35-8] CDC CDC [ ] NIST ACE2008 GEDR CDC 1 1 CDC John Smiths [

Size: px

Start display at page:

Download "ognitiongedr) CDC JHU ACE2005 CDC ACE2005 IBM CDC ACE2005 CDC 1 ACE [35-8] CDC CDC [ ] NIST ACE2008 GEDR CDC 1 1 CDC John Smiths ["

镀葛
5 years ago
Views:

1 JOURNAL OFCHINESEINFORMATION PROCESSING Vol.29No.1 Jan (2015) ( ) ( ) (CrossDocumentCoreferenceCDC) CDC ACE2005 ACE CDC TP391 A ConstructionofInformationExtraction-orientatedChinese CrossDocumentCoreferenceCorpus ZHAOZhiweiQIAN LonghuaZHOU Guodong (1.NaturalLanguageProcessingLaboratorySoochow UniversitySuzhouJiangsu215006China 2.SchoolofComputerScience & TechnologySoochow UniversitySuzhouJiangsu215006China) 1 [2] [3] AbstractCrossDocumentCoreference(CDC)resolutionisanimportantstepininformationintegrationandinforma- tionfusion.asaconsequenceacdccorpusisindispensableforresearchandevaluationofcdcresolution.given thefactthatnochinesecdccorpusispubliclyavailableorientedforinformationextractionthispaperdescribes howtobuildacdccorpusbasedontheace2005chinesecorpusviaautomaticgenerationandmanualannotation whichcoversaltheaceentitytypes.thecorpusismadepubliclyavailabletoadvancetheresearchonchinese CDCresolution.InadditionthispaperanalysesthetypesandcharacteristicsofCDCinChinesetextaswelaspro- posestheconceptoftwometricsi.e. variationperplexity and ambiguityperplexity toevaluatethedificulty ofchinesecdcresolutionprovidingsomeinsightsforfurthercdcresearch. Keywordscrossdocumentcoreferenceinformationextractioncorporaannotationperplexity MUC-6 [4] (CrossDocumentCo-referenceCDC) [1] ACE2008 [5] (GlobalEntityDetectionandRec ( ) (BK KJA520003)

2 ognitiongedr) CDC JHU ACE2005 CDC ACE2005 IBM CDC ACE2005 CDC 1 ACE [35-8] CDC CDC [ ] NIST ACE2008 GEDR CDC 1 1 CDC John Smiths [6] WePS2007 [9] CIPS2010 [10] ACE2008 [5] Wikipedia 4.3 WEB LinkCorpus [11] 150 Person-X [7] zip htp//nlp.suda.edu.cn/~qianlonghua/ace2005-cdc.

3 1 59 ACE CDC [12] ACE CDC 6771 CDC WEB (ORG) a)web WEB [6] JohnSmiths [11] WikiLink WePS [9] CIPS [10] ACE2008 JHU2007CLSP ACE2005CDC Person-X [7] ACE2005 Person-X CDC Singh [11] ACE2008 CDC CDC PER ORG GPE CDC 2419 CDC ACE2008 GEDR GRDR(GlobalRelation [12] ACE2005 CDC ACE2005 CDC 85.4% b) CDC CDC CDC NIST ACE2005 Detectionand Recognition) TAC CDC ACE2008 (TextAnalysisConference) KBP (Knowl- edgebasepopulation) [13] (PER) (EntityLinking)

60 2015 ( ) (EntityDisambiguation) [14] ID 3.2 (Infobox) 3.

4 ( ) (EntityDisambiguation) [14] ID 3.2 (Infobox) 3.3 [15-16] Web [9] Web [14] A B Web 3 ACE (headword) 3.1 ACE XML ACE XML XML C 1 CDC

1 61 4.1 a) Passoneau [17] Krippendorf [18] alpha Passoneau b) 0 GPE 0.33 0.67 1 3.4 2

5 a) Passoneau [17] Krippendorf [18] alpha Passoneau b) 0 GPE CDC ID ENT TYPE ENTITY DOC ID ( ) FAC MENTION 299 GPE 2419 LOC 233 ORG 2 CDC 4 CDC alpha 96% Krippendorf 67% alpha 1939 PER 1860 VEH WEA % GPE 85% 55%ORG PER LOC FAC GPE 4.2.2

6 CDC CDC 40% 7% GPE BandaAceh ACE ORG DPRK(DemocraticPeople s RepublicofKorea) PER 2 ACE ACE 2 3 /% GPE

7 1 63 H v E( i) E i =- j=1 pj log p( j ) (1) C e H v ( C) = w e i H v (E i ) (2) i=1 PP v =2 H v() C (3) H v (E i ) E i H v (C) w i e E i C e 100% PP v /% Popescu [19] Popescu M i CDC (PP r ) E i m j c j E i m j E i Ψ E( i) = E m{ j} i j=1 E i E i C e pj m j PP v C m E i pj =c / j c k PP r k=1 (1)~(3) B3 [20] (PP r ) (PP v )

8 B3 TF*IDF 5 B3 ACE CDC F ACE GPE ORG PER CDC [321] CDC ACE2005 CDC CDC ( ) ( ) [1] DaganIItaiA.AutomaticProcessingofLargeCor- porafortheresolutionofanaphorareferences[c]// Proceedingsofthe13thconferenceon Computational linguistics.stroudsburgpausahanskarlgren [2]. [D] [3] MayfieldJAlexanderDDorrBetal.Cross-Docu- mentcoreferenceresolutiona Key Technologyfor Learningby Reading[C]//Proceedingsofthe AAAI

1 65 2009SpringSymposium onlearningby Readingand Learningto Read.StanfordCalifornia March 23 200965-70. ence-6abriefhistory[c]//proceedingsofthe16th Conferenceon ComputationalLinguistics (COLING' 96).

gov/speech/tests/ace/2008/doc/ ace08-evalplan.v1.2d.pdf2008. [6] Bagga ABaldwin B.Entity-Based Cross-Document Coreferencing Usingthe VectorSpace Model[C]// [4] GrishmanRBethS.

9 SpringSymposium onlearningby Readingand Learningto Read.StanfordCalifornia March ence-6abriefhistory[c]//proceedingsofthe16th Conferenceon ComputationalLinguistics (COLING' 96).CopenhagenDenmarkAugust [5] NISTSpeechGroup.TheACE2008evaluationplan AssessmentofDetectionand RecognitionofEntities andrelationswithinandacrossdocuments[eb/ol]. htp// ace08-evalplan.v1.2d.pdf2008. [6] Bagga ABaldwin B.Entity-Based Cross-Document Coreferencing Usingthe VectorSpace Model[C]// [4] GrishmanRBethS.MessageUnderstandingConfer- Proceedingsofthe36thAnnualMeetingoftheAssoci- ationforcomputationallinguisticsandthe17thinter- national Conference on Computational Linguistics (COLING-ACL'98). Montréal Québec Canada [7] GooiC HAlanJ.Cross-DocumentCoreferenceona LargeScaleCorpus[C]//ProceedingsofHLT-NAACL 2004.USA [8] Batista-NavarroR TAnaniadouS.BuildingaCoref- erence-annotatedcorpusfromthedomainofbiochem- istry[c]//proceedingsofthe2011 WorkshoponBio- medical Natural Language Processing ACL-HLT 2011.PortlandOregonUSAJune [9] ArtilesJGonzaloJSekineS.Web PeopleSearch TaskatSemEval-2007[EB/OL].htp//nlp.uned.es/ weps/weps2007 data readme 1.1.txt2007 [10] CIPS-SIGHAN Joint Conference on Chinese Lan- guage Processing (CLP2010)[EB/OL]. htp// ch.htm2010. [11] Singh SSubramanya APereira Fetal.Large- ScaleCross-DocumentCoreferenceUsingDistributed Inferenceand Hierarchical Models[C]//Proceedings ofthe49th Annual Meetingofthe Associationfor ComputationalLinguistics.PortlandOregon [12] CLSPSummerWorkshop.ExploitingLexical& En- cyclopedicresourcesforentitydisambiguation[eb/ OL].htp// elerfed/documents/elerfed-cdc-overview. v2. ppt2007. [13] TaskDescriptionfor KnowledgeBasePopulationat TAC 2009[EB/OL].htp//apl.jhu.edu/~paul- mac/kbp/ kbptaskguidelines.pdf2009 [14]. [J] (6) [15] Rao D McNamee PDredze M.Entity Linking Finding Extracted Entitiesin a Knowledge Base Multi-source Multi-lingual Information Extraction andsummarization[m].germanyspringer2011. ationbasedon Wikipedia Data[C]//Proceedingsof EmpiricalMethodsin NaturalLanguageProcessing. PragueJune [16] Cucerzan S.Large-Scale Named Entity Disambigu- [17] PassoneauRJ.Computingreliabilityforcoreference annotation[c]//proceedingsoftheinternationalcon- ferenceon Language Resouces (LREC).Lisbon PortugalMay2004. [18] KrippendorfK H.ContentAnalysisAnIntroduc- tiontoits Methodology[M].Beverly HilsCA SagePublications1980. [19] PopescuO.PersonCrossDocumentCoreferencewith NamePerplexity Estimates[C]//Proceedingsofthe 2009 Conference on Empirical Methodsin Natural LanguageProcessing.Singapore6-7 August adaspainmay1998. [21] Baron AFreedman M.Whois Whoand Whatis WhatExperimentsinCross-DocumentCo-Reference [20] BaggaA.EvaluationofCoreferencesandCoreference Resolution Systems[C]//Proceedings ofthe First LanguageResourceandEvaluationConference.Gran- [C]//Proceedingsofthe2008ConferenceonEmpiri- calmethodsinnaturallanguageprocessing.hono- luluoctober (1987 ) none.zhao@gmail.com (1966 ) qianlonghua@suda.edu.cn

66 2015 (1967 ) E-mailgdzhou@ suda.edu.cn 櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚 ( 48 ) [8] PeterLinz.

[J]. [14] ZhangKunliZhang WencongZan Hongyingetal. ( )200842(2)190-194. Studiesonautomaticrecognitionofseveralcommon [10].

Chinese wordsegmentation anditsefectoninformationretrieval[j].informa- tionprocessingand Management200440(1)161-191.

[13] LafertyJMcCalum APereiraF.ConditionalRan- [C]//Proceedingsofthe10thChineseLexicalSeman- tics Workshop. 200931-37.

10 (1967 ) gdzhou@ suda.edu.cn 櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚櫚 ( 48 ) [8] PeterLinz. dom FieldsProbabilistic ModelsforSegmentingand [M] LabelingSequenceData[C]//Proceedingsofthe18th [9]. ICML [J]. [14] ZhangKunliZhang WencongZan Hongyingetal. ( )200842(2) Studiesonautomaticrecognitionofseveralcommon [10]. Chineseadverbs usagesbasedonbpneuralnetworks [J] [11] SchubertFooHuiLi.Chinese wordsegmentation anditsefectoninformationretrieval[j].informa- tionprocessingand Management200440(1) [12] GeorgeA Miler.WordNetA LexicalDatabasefor English[C]//ProceedingsofCommunicationsofthe ACM [13] LafertyJMcCalum APereiraF.ConditionalRan- [C]//Proceedingsofthe10thChineseLexicalSeman- tics Workshop [15] LovaszLPlummer M D. Matchingtheory [M]. AmsterdamElsevierScience2009. [16].BFS-CTC [J] (1) [17]. [J] (6) (1968 ) jiasuimin@163.com (1986 ) leili lei@163.com (1973 ) hero jack@163.com

<4D6963726F736F667420576F7264202D20BBB3BBAFD1A7D4BA32303134C4EAB1CFD2B5C9FABECDD2B5D6CAC1BFB1A8B8E62E646F63>

<4D6963726F736F667420576F7264202D20BBB3BBAFD1A7D4BA32303134C4EAB1CFD2B5C9FABECDD2B5D6CAC1BFB1A8B8E62E646F63> 唯唯唯 2014 年毕业生就业质量报告唯唯唯唯 2014 年 12 月目录 1 引言 2 1 2014 届业生本情况 3 1.1 业生总体情况.. 3 1.2 业生生源地情况.. 3 1.3 业生学科业情况.. 4 1.4 业生性结构.. 5 2 2014 届业生就业情况. 5 2.1 总就业情