持续中断?论统计机器翻译向神经机器翻译的转变

IF 0.8 Q3 LINGUISTICS Tradumatica-Traduccio i Tecnologies de la Informacio i la Comunicacio Pub Date : 2018-12-03 DOI:10.5565/REV/TRADUMATICA.221

D. Kenny

{"title":"持续中断?论统计机器翻译向神经机器翻译的转变","authors":"D. Kenny","doi":"10.5565/REV/TRADUMATICA.221","DOIUrl":null,"url":null,"abstract":"If statistical machine translation (SMT) was a disruptive technology, then neural machine translation (NMT) is probably a sustaining technology, continuing on a trajectory already established by SMT, and initially evaluated in much the same way as its predecessor. Seeing NMT in this light may be a useful corrective to the hype that has surrounded its introduction.","PeriodicalId":42402,"journal":{"name":"Tradumatica-Traduccio i Tecnologies de la Informacio i la Comunicacio","volume":"400 1","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2018-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Sustaining Disruption? On the Transition from Statistical to Neural Machine Translation\",\"authors\":\"D. Kenny\",\"doi\":\"10.5565/REV/TRADUMATICA.221\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"If statistical machine translation (SMT) was a disruptive technology, then neural machine translation (NMT) is probably a sustaining technology, continuing on a trajectory already established by SMT, and initially evaluated in much the same way as its predecessor. Seeing NMT in this light may be a useful corrective to the hype that has surrounded its introduction.\",\"PeriodicalId\":42402,\"journal\":{\"name\":\"Tradumatica-Traduccio i Tecnologies de la Informacio i la Comunicacio\",\"volume\":\"400 1\",\"pages\":\"\"},\"PeriodicalIF\":0.8000,\"publicationDate\":\"2018-12-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tradumatica-Traduccio i Tecnologies de la Informacio i la Comunicacio\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5565/REV/TRADUMATICA.221\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"LINGUISTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tradumatica-Traduccio i Tecnologies de la Informacio i la Comunicacio","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5565/REV/TRADUMATICA.221","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"LINGUISTICS","Score":null,"Total":0}

引用次数: 11

摘要

如果统计机器翻译(SMT)是一种破坏性的技术，那么神经机器翻译(NMT)可能是一种可持续的技术，继续沿着SMT已经建立的轨迹发展，并以与其前身大致相同的方式进行初步评估。从这个角度来看NMT可能是对围绕其引入的炒作的有益纠正。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Sustaining Disruption? On the Transition from Statistical to Neural Machine Translation

If statistical machine translation (SMT) was a disruptive technology, then neural machine translation (NMT) is probably a sustaining technology, continuing on a trajectory already established by SMT, and initially evaluated in much the same way as its predecessor. Seeing NMT in this light may be a useful corrective to the hype that has surrounded its introduction.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊