Automatic learning for semantic collocation

Automatic learning for semantic collocation

ID:37657047

大小:680.71 KB

页数:7页

时间:2019-05-27

Automatic learning for semantic collocation_第1页
Automatic learning for semantic collocation_第2页
Automatic learning for semantic collocation_第3页
Automatic learning for semantic collocation_第4页
Automatic learning for semantic collocation_第5页
资源描述:

《Automatic learning for semantic collocation》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库

1、AutomaticLearningforSemanticCollocationSatoshlSEKINE*TokyoInformationandCommunicationsResearchLaboratoryMatsushitaElectricIndustrialCo.,Ltd.3-10-1,higashimita,tama-ku,kawasaki214JAPANJeremyJ.CARROLLSofiaANANIADOUJun'ichiTSUJIICentreforComputationalLinguisticsUniv

2、ersityofManchesterInstituteofScienceandTechnologyP.O.Box88,ManchesterM601QD,UnitedKingdomAbstractguisticorextra-linguistic.Inparticular,ithasbeenre-ported[Ananiadou,1990]thatnotonlyextra-linguistic,Therealdifficultyindevelopmentofpracticaldomainknowledgebutalsoli

3、nguisticknowledgerequiredNLPsystemscomesfromthefactthatwedoforapplicationsystemsvaries,dependingontext-typenothaveeffectivemeansforgathering"knowl-(technicalreports,scientificpapers,manuals,etc.),sub-edge".Inthispaper,weproposeanalgorithmjectdomain,typeofapplicat

4、ion(MT,automaticab-whichacquiresautomaticallyknowledgeofse-straction,etc.)etc.Thismeansthatwehavetohaveef-manticcollocationsamong"words"fromsam-fectiveandefficientmethodseitherforadaptingalreadyplecorpora.existingknowledgeforaspecific"sublanguage"orforac-Thealgor

5、ithmproposedinthispapertriestoquiringknowledgeautomatically,forexamplefromsam-discoversemanticcollocationswhichwillbeplecorporaofgivenapplications.usefulfordisambiguatingstructurallyambigu-Inthispaper,weproposeanalgorithmwhichauto-oussentences,byastatisticalappro

6、ach.Thematicallyacquiresknowledgeofsemanticcollocationsalgorithmrequiresacorpusandminimumlin-among"words"."Semantic"heremeansthatthecol-guisticknowledge(parts-of-speechofwords,locationsthealgorithmdiscoversarenotcollocationssimpleinflectionrules,andasmallnumberof

7、amongwordsinthesenseoftraditionallinguisticsbutgeneralsyntacticrules).collocationsthatreflectontologicalrelationsamongen-Weconductedtwoexperimentsofapplyingthetitiesingivensubjectdomains.Weexpectthatthealgorithmtodifferentcorporatoextractdif-knowledgetobeextracte

8、dwillnotonlybeusefulforferenttypesofsemanticcollocations.Thoughdisambiguatingsentencesbutalsowillcontributetodis-therearesomeunsolvedproblems,theresultscoverin

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。