文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > INTERSPEECH 2006- ICSLP Linguistic tuple segmentation in ngram-based statistical machine tr
侵权投诉

INTERSPEECH 2006- ICSLP Linguistic tuple segmentation in ngram-based statistical machine tr

Ngram-based Statistical Machine Translation relies on a standard Ngram language model of tuples to estimate the translation process. In training, this translation model requires a segmentation of each parallel sentence, which involves taking a hard decisio

Linguistictuplesegmentationinngram-basedstatisticalmachinetranslation

Adri`adeGispert,Jos´eB.Mari no

TALPResearchCenter

UniversitatPolit`ecnicadeCatalunya(UPC),Barcelona

{agispert|canton}@gps.tsc.upc.edu

Abstract

Ngram-basedStatisticalMachineTranslationreliesonastandard

Ngramlanguagemodeloftuplestoestimatethetranslationpro-cess.Intraining,thistranslationmodelrequiresasegmentationofeachparallelsentence,whichinvolvestakingaharddecisionontuplesegmentationwhenawordisnotlinkedduringwordalign-ment.Thisisespeciallycriticalwhenthiswordappearsinthetargetlanguage,asthisharddecisioniscompulsory.

Inthispaperwepresentathoroughstudyofthissituation,comparingforthe rsttimeeachoftheproposedtechniquesintwoindependenttasks,namelyEnglish–SpanishEuropeanParlia-mentProceedingslarge-vocabularytaskandArabic–EnglishBasicTravelExpressionssmall-datatask.Inthefaceofthiscomparison,wepresentanovelsegmentationtechniquewhichincorporateslin-guisticinformation.Resultsobtainedinbothtasksoutperformallprevioustechniques.

IndexTerms:statisticalmachinetranslation,tuplesegmentation,n-gram-basedSMT,linguisticinformation

cannotbeallowed,andacertainharddecisionmustbetakenre-gardingtuplesegmentation,asin gure1.

Literatureoffersexamplesofcriteriatodecidethissegmenta-tion,rangingfromsimplylinkingthetargetwordsoftheNULL-sourcetupletothepreviousornexttuple(ifthereisany)deter-ministically,tocomparingtheIBMmodel1scoreassignedtotheresultingtuplesoftwocompetingsegmentations

INTERSPEECH 2006- ICSLP Linguistic tuple segmentation in ngram-based statistical machine tr

[6].

Figure1:AhardsegmentationdecisionmustbetakenHowever,toourknowledgetheimpactofthissegmentationdecisionontranslationqualityisnotstudied,northealternativesegmentationstrategiesarecompared.Here,wecarryoutthiscomparison,exploringtheimpactofthisharddecisioninNgramtranslationmodelestimationandintranslationquality,andwepro-poseanovelstrategywhichfollowsalinguisticcriteriatoindi-rectlyreducethemodelentropy.WeperformthiscomparisoninanEnglish-to-Spanish(andviceversa)large-vocabularytask,andadditionallyinanArabic-to-Englishsmall-vocabularytask.Fur-thermore,westudytheeffectontranslationofNULLtokenswhentheseoccurinthetargetsideofthetuple.

1.Introduction

Ngram-based(orTuple-based)StatisticalMachineTranslation(SMT)hasprovedtobeastate-of-the-artalternativeapproachtophrase-basedmodelsinperformancecomparisons[1,2].ItsmaindistinctivetreatistheestimationofthecoretranslationmodelbymeansofastandardNgramlanguagemodel,de nedonthespecialbilinguallanguageexpressedbytuples[3].

Accordingtoliterature,tuplesareunitscontainingoneormoresource-languagewordsandoneormoretarget-languagewords(in-cludingtheNULLtoken,whichisinfactnoword).ThismodelhasitsoriginsinmachinetranslationusingFinite-StateTransduc-ers[4],whosetheoreticalfoundationexpressesthatweseekthetargetsentence’e’maximising:

NYn=1

2.TupleSegmentationstrategies

AccordingtotheaforementionedconceptualframeworkofNgram

translationmodel,itseemsclearthattheidealtuplesegmentationstrategyshouldtakeaglobaldecisionbasedonthesegmentationforallotherNULL-sourcecases,attemptingtoobtainthatsetoftuplesandNgramswhichbetterrepresentedtheunseenuniverseofevents,meaningtheonewithlessentropy.However,nofeasiblealgorithmcanperformthatcalculationinareasonabletimegivencurrentcomputationalpower,asthiswouldinvolveawholemodelreestimationforeachparticularsegmentationalternative.

SofartwosegmentationstrategiestosolvethesourceNULLproblemhavebeenproposed,whicharepresentedinthenextsec-tions,togetherwithanovelstrategybasedonalinguisticcriterion.2.1.DeterministicalwaysNEXT

Averypragmaticandsimpleapproachistoalwaysjointhetar-getwordsinvolvedinNULLlinks(NULL-linkedwords)tothenexttuple,ifthereisany(otherwisetothepreviousone),as rstdonein[7].Besidessimplicityandextremeef ciency,wedonotobserveanyotheradvantageofthisapproach,whichontheotherhanddoesnotfollowanylinguisticorstatisticalcriterion.

p((f,e)n|(f,e)n x+1,...,(f,e)n 1)

(1)

wherethen-thtupleofasentencepairisreferredas(f,e)n.Inordertoestimatethislanguagemodelparameters,givenaparallelcorpusandacertainwordalignment,andincontrasttophrase-basedapproaches,thetrainingrequiresauniquesegmentationofeachbilingualpairofsentencesintoasequenceoftuplessothatthenaturalorderofbothlanguagesisnotviolated[5].

Thestandardtupleextractionalgorithm[5]de nesauniquesetoftuplesexceptwhenevertheresultingtuplecontainsnosourceword(NULL-sourcetuple).Inordertore-usetheseunitsinde-codingnewsentences,thesearchshouldallowfornoinputwordtogenerateunits,andthisisnotthecase.Therefore,theseunits

第1页

你可能喜欢

热门文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email