适应非中心语言的零射击多语种翻译

Zhi Qu, Taro Watanabe
{"title":"适应非中心语言的零射击多语种翻译","authors":"Zhi Qu, Taro Watanabe","doi":"10.48550/arXiv.2209.04138","DOIUrl":null,"url":null,"abstract":"Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination of central language, e.g. English, we supplement this viewpoint with the strict dependence of non-centered languages. In this work, we propose a simple, lightweight yet effective language-specific modeling method by adapting to non-centered languages and combining the shared information and the language-specific information to counteract the instability of zero-shot translation. Experiments with Transformer on IWSLT17, Europarl, TED talks, and OPUS-100 datasets show that our method not only performs better than strong baselines in centered data conditions but also can easily fit non-centered data conditions. By further investigating the layer attribution, we show that our proposed method can disentangle the coupled representation in the correct direction.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"6 1","pages":"5251-5265"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Adapting to Non-Centered Languages for Zero-shot Multilingual Translation\",\"authors\":\"Zhi Qu, Taro Watanabe\",\"doi\":\"10.48550/arXiv.2209.04138\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination of central language, e.g. English, we supplement this viewpoint with the strict dependence of non-centered languages. In this work, we propose a simple, lightweight yet effective language-specific modeling method by adapting to non-centered languages and combining the shared information and the language-specific information to counteract the instability of zero-shot translation. Experiments with Transformer on IWSLT17, Europarl, TED talks, and OPUS-100 datasets show that our method not only performs better than strong baselines in centered data conditions but also can easily fit non-centered data conditions. By further investigating the layer attribution, we show that our proposed method can disentangle the coupled representation in the correct direction.\",\"PeriodicalId\":91381,\"journal\":{\"name\":\"Proceedings of COLING. International Conference on Computational Linguistics\",\"volume\":\"6 1\",\"pages\":\"5251-5265\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of COLING. International Conference on Computational Linguistics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2209.04138\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of COLING. International Conference on Computational Linguistics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2209.04138","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

多语言神经机器翻译可以在训练过程中翻译未见过的语言对,即零射击翻译。然而,零点平移总是不稳定的。虽然先前的研究将这种不稳定归因于中心语言(如英语)的统治,但我们补充了非中心语言的严格依赖。在这项工作中,我们提出了一种简单,轻量级但有效的特定语言建模方法,通过适应非中心语言,将共享信息和特定语言信息相结合来抵消零射击翻译的不稳定性。Transformer在IWSLT17、Europarl、TED talks和OPUS-100数据集上的实验表明,我们的方法不仅在中心数据条件下优于强基线,而且可以很容易地拟合非中心数据条件。通过对层属性的进一步研究,我们证明了我们的方法可以在正确的方向上解开耦合表示。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Adapting to Non-Centered Languages for Zero-shot Multilingual Translation
Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination of central language, e.g. English, we supplement this viewpoint with the strict dependence of non-centered languages. In this work, we propose a simple, lightweight yet effective language-specific modeling method by adapting to non-centered languages and combining the shared information and the language-specific information to counteract the instability of zero-shot translation. Experiments with Transformer on IWSLT17, Europarl, TED talks, and OPUS-100 datasets show that our method not only performs better than strong baselines in centered data conditions but also can easily fit non-centered data conditions. By further investigating the layer attribution, we show that our proposed method can disentangle the coupled representation in the correct direction.
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
自引率
0.00%
发文量
0
期刊最新文献
Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension Event Causality Extraction with Event Argument Correlations BERT-Flow-VAE: A Weakly-supervised Model for Multi-Label Text Classification TestAug: A Framework for Augmenting Capability-based NLP Tests Multilingual Word Sense Disambiguation with Unified Sense Representation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1