命名实体音译的神经机器翻译技术

NEWS@ACL Pub Date : 2018-07-01 DOI:10.18653/v1/W18-2413

Roman Grundkiewicz, Kenneth Heafield

{"title":"命名实体音译的神经机器翻译技术","authors":"Roman Grundkiewicz, Kenneth Heafield","doi":"10.18653/v1/W18-2413","DOIUrl":null,"url":null,"abstract":"Transliterating named entities from one language into another can be approached as neural machine translation (NMT) problem, for which we use deep attentional RNN encoder-decoder models. To build a strong transliteration system, we apply well-established techniques from NMT, such as dropout regularization, model ensembling, rescoring with right-to-left models, and back-translation. Our submission to the NEWS 2018 Shared Task on Named Entity Transliteration ranked first in several tracks.","PeriodicalId":189654,"journal":{"name":"NEWS@ACL","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"28","resultStr":"{\"title\":\"Neural Machine Translation Techniques for Named Entity Transliteration\",\"authors\":\"Roman Grundkiewicz, Kenneth Heafield\",\"doi\":\"10.18653/v1/W18-2413\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Transliterating named entities from one language into another can be approached as neural machine translation (NMT) problem, for which we use deep attentional RNN encoder-decoder models. To build a strong transliteration system, we apply well-established techniques from NMT, such as dropout regularization, model ensembling, rescoring with right-to-left models, and back-translation. Our submission to the NEWS 2018 Shared Task on Named Entity Transliteration ranked first in several tracks.\",\"PeriodicalId\":189654,\"journal\":{\"name\":\"NEWS@ACL\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"28\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"NEWS@ACL\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/W18-2413\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"NEWS@ACL","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/W18-2413","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 28

摘要

将命名实体从一种语言音译为另一种语言可以作为神经机器翻译(NMT)问题来处理，为此我们使用了深度注意RNN编码器-解码器模型。为了建立一个强大的音译系统，我们应用了NMT中成熟的技术，如dropout正则化、模型集成、从右到左模型评分和反向翻译。我们提交给NEWS 2018的关于命名实体音译的共享任务在几个方面排名第一。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Neural Machine Translation Techniques for Named Entity Transliteration

Transliterating named entities from one language into another can be approached as neural machine translation (NMT) problem, for which we use deep attentional RNN encoder-decoder models. To build a strong transliteration system, we apply well-established techniques from NMT, such as dropout regularization, model ensembling, rescoring with right-to-left models, and back-translation. Our submission to the NEWS 2018 Shared Task on Named Entity Transliteration ranked first in several tracks.

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

NEWS@ACL

自引率

0.00%

发文量