欢迎来到天天文库
浏览记录
ID:34931807
大小:1.20 MB
页数:175页
时间:2019-03-14
《2008-PHD-Global Inference for Sentence Compression An Integer Linear Programming Approach.pdf》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库。
1、GlobalInferenceforSentenceCompression:AnIntegerLinearProgrammingApproachJamesClarkeNIVERUSEITHYTOHFGERDUINBDoctorofPhilosophyInstituteforCommunicatingandCollaborativeSystemsSchoolofInformaticsUniversityofEdinburgh2008AbstractInthisthesiswedevelopmodelsforsentencecompression.Thistex
2、trewritingtaskhasrecentlyattractedalotofattentionduetoitsrelevanceforapplications(e.g.,sum-marisation)andsimpleformulationbymeansofworddeletion.Previousmodelsforsentencecompressionhavebeeninherentlylocalandthusfailtocapturethelongrangedependenciesandcomplexinteractionsinvolvedintex
3、trewriting.Wepresentasolu-tionbyframingthetaskasanoptimisationproblemwithlocalandglobalconstraintsandrecastexistingcompressionmodelsintothisframework.Usingtheconstraintsweinstillsyntactic,semanticanddiscourseknowledgethemodelsotherwisefailtocap-ture.Weshowthattheadditionofconstrain
4、tsallowrelativelysimplelocalmodelstoreachstate-of-the-artperformanceforsentencecompression.Thethesisprovidesadetailedstudyofsentencecompressionanditsmodels.Thedifferencesbetweenautomaticandmanuallycreatedcompressioncorporaareassessedalongwithhowcompressionvariesacrosswrittenandspok
5、entext.Wealsodis-cussvarioustechniquesforautomaticallyandmanuallyevaluatingcompressionoutputagainstagoldstandard.Modelsarereviewedbasedontheirassumptions,trainingre-quirements,andscalability.Weintroduceageneralmethodforextendingpreviousapproachestoallowformoreglobalmodels.Thisisach
6、ievedthroughtheoptimisationframeworkofIntegerLinearProgramming(ILP).Wereformulatethreecompressionmodels:anunsuper-visedmodel,asemi-supervisedmodelandafullysupervisedmodelasILPproblemsandaugmentthemwithconstraints.Theseconstraintsareintuitiveforthecompressiontaskandarebothsyntactica
7、llyandsemanticallymotivated.Wedemonstratehowtheyimprovecompressionqualityandreducetherequirementsontrainingmaterial.Finally,wedelveintodocumentcompressionwherethetaskistocompressev-erysentenceofadocumentandusetheresultingsummaryasareplacementfortheoriginaldocument.Fordocument-based
8、compressionweinvestigatedi
此文档下载收益归作者所有