多路转换器:一种基于头部可配置变压器的直接语音翻译模型

Gerard Sant, Gerard I. Gállego, Belen Alastruey, M. Costa-jussà
{"title":"多路转换器:一种基于头部可配置变压器的直接语音翻译模型","authors":"Gerard Sant, Gerard I. Gállego, Belen Alastruey, M. Costa-jussà","doi":"10.48550/arXiv.2205.07100","DOIUrl":null,"url":null,"abstract":"Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as long sequence lengths and redundancy between adjacent tokens. Therefore, we believe that regular self-attention mechanism might not be well suited for it. Different approaches have been proposed to overcome these problems, such as the use of efficient attention mechanisms. However, the use of these methods usually comes with a cost, which is a performance reduction caused by information loss. In this study, we present the Multiformer, a Transformer-based model which allows the use of different attention mechanisms on each head. By doing this, the model is able to bias the self-attention towards the extraction of more diverse token interactions, and the information loss is reduced. Finally, we perform an analysis of the head contributions, and we observe that those architectures where all heads relevance is uniformly distributed obtain better results. Our results show that mixing attention patterns along the different heads and layers outperforms our baseline by up to 0.7 BLEU.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"408 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation\",\"authors\":\"Gerard Sant, Gerard I. Gállego, Belen Alastruey, M. Costa-jussà\",\"doi\":\"10.48550/arXiv.2205.07100\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as long sequence lengths and redundancy between adjacent tokens. Therefore, we believe that regular self-attention mechanism might not be well suited for it. Different approaches have been proposed to overcome these problems, such as the use of efficient attention mechanisms. However, the use of these methods usually comes with a cost, which is a performance reduction caused by information loss. In this study, we present the Multiformer, a Transformer-based model which allows the use of different attention mechanisms on each head. By doing this, the model is able to bias the self-attention towards the extraction of more diverse token interactions, and the information loss is reduced. Finally, we perform an analysis of the head contributions, and we observe that those architectures where all heads relevance is uniformly distributed obtain better results. Our results show that mixing attention patterns along the different heads and layers outperforms our baseline by up to 0.7 BLEU.\",\"PeriodicalId\":382084,\"journal\":{\"name\":\"North American Chapter of the Association for Computational Linguistics\",\"volume\":\"408 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"North American Chapter of the Association for Computational Linguistics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2205.07100\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"North American Chapter of the Association for Computational Linguistics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2205.07100","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

基于变压器的模型已经在自然语言处理的几个领域取得了最先进的成果。然而,它在语音任务中的直接应用并非微不足道。这种序列的本质带来了诸如长序列长度和相邻令牌之间的冗余等问题。因此,我们认为常规的自我注意机制可能不太适合它。已经提出了不同的方法来克服这些问题,例如使用有效的注意机制。然而,使用这些方法通常是有代价的,即由于信息丢失而导致的性能下降。在这项研究中,我们提出了Multiformer,一个基于变压器的模型,允许在每个头部使用不同的注意机制。通过这样做,模型能够将自注意力偏向于提取更多样化的令牌交互,并减少信息损失。最后,我们对头部贡献进行了分析,我们观察到所有头部相关均匀分布的架构获得了更好的结果。我们的结果表明,沿着不同的头部和层次混合注意力模式比我们的基线高出0.7 BLEU。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation
Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as long sequence lengths and redundancy between adjacent tokens. Therefore, we believe that regular self-attention mechanism might not be well suited for it. Different approaches have been proposed to overcome these problems, such as the use of efficient attention mechanisms. However, the use of these methods usually comes with a cost, which is a performance reduction caused by information loss. In this study, we present the Multiformer, a Transformer-based model which allows the use of different attention mechanisms on each head. By doing this, the model is able to bias the self-attention towards the extraction of more diverse token interactions, and the information loss is reduced. Finally, we perform an analysis of the head contributions, and we observe that those architectures where all heads relevance is uniformly distributed obtain better results. Our results show that mixing attention patterns along the different heads and layers outperforms our baseline by up to 0.7 BLEU.
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
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信