Neural Machine Translation

Neural Machine Translation

ID:40947158

大小:425.78 KB

页数:15页

时间:2019-08-11

Neural Machine Translation_第1页
Neural Machine Translation_第2页
Neural Machine Translation_第3页
Neural Machine Translation_第4页
Neural Machine Translation_第5页
资源描述:

《Neural Machine Translation》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、NeuralMachineTranslationbyJointlyLearningtoAlignandTranslateDzmitryBahdanauKyungHyunChoYoshuaBengioJacobsUniversity,GermanyUniversitedeMontr´eal´UniversitedeMontr´eal´CIFARSeniorFellowAbstractNeuralmachinetranslationisarecentlyproposedapproachtomachin

2、etransla-tion.Unlikethetraditionalstatisticalmachinetranslation,theneuralmachinetranslationaimsatbuildingasingleneuralnetworkthatcanbejointlytunedtomaximizethetranslationperformance.Themodelsproposedrecentlyforneuralmachinetranslationoftenbelongtoafam

3、ilyofencoder–decodersandencodesasourcesentenceintoafixed-lengthvectorfromwhichadecodergeneratesatranslation.Inthispaper,weconjecturethattheuseofafixed-lengthvectorisabottleneckinimprovingtheperformanceofthisbasicencoder–decoderarchitec-ture,andproposeto

4、extendthisbyallowingamodeltoautomatically(soft-)searchforpartsofasourcesentencethatarerelevanttopredictingatargetword,withouthavingtoformthesepartsasahardsegmentexplicitly.Withthisnewapproach,weachieveatranslationperformancecomparabletotheexistingstat

5、e-of-the-artphrase-basedsystemonthetaskofEnglish-to-Frenchtranslation.Furthermore,qualitativeanalysisrevealsthatthe(soft-)alignmentsfoundbythemodelagreewellwithourintuition.1IntroductionNeuralmachinetranslationisanewlyemergingapproachtomachinetranslat

6、ion,recentlyproposedbyKalchbrennerandBlunsom(2013),Sutskeveretal.(2014)andChoetal.(2014b).Unlikethetraditionalphrase-basedtranslationsystem(see,e.g.,Koehnetal.,2003)whichconsistsofmanysmallsub-componentsthataretunedseparately,neuralmachinetranslationa

7、ttemptstobuildandarXiv:1409.0473v2[cs.CL]4Sep2014trainasingle,largeneuralnetworkthatreadsasentenceandoutputsacorrecttranslation.Mostoftheproposedneuralmachinetranslationmodelsbelongtoafamilyofencoder–decoders(Sutskeveretal.,2014;Choetal.,2014a),withan

8、encoderandadecoderforeachlan-guage,orinvolvealanguage-specificencoderappliedtoeachsentencewhoseoutputsarethencom-pared(HermannandBlunsom,2014).Anencoderneuralnetworkreadsandencodesasourcesen-tenceintoafixed-lengthvector.Adecoderthenoutputsatrans

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。