Generating Repetitions with Appropriate Repeated Words

Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, M. Okumura
{"title":"Generating Repetitions with Appropriate Repeated Words","authors":"Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, M. Okumura","doi":"10.48550/arXiv.2207.00929","DOIUrl":null,"url":null,"abstract":"A repetition is a response that repeats words in the previous speaker’s utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","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.2207.00929","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

A repetition is a response that repeats words in the previous speaker’s utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.
用适当的重复单词产生重复
重复是在对话中重复前一个说话者话语中的单词的反应。正如语言学研究所调查的那样,重复在与他人建立信任的交流中是必不可少的。在这项工作中,我们专注于重复生成。据我们所知,这是第一个解决重复生成的神经方法。我们提出了加权标签平滑,一种在微调过程中明确学习重复单词的平滑方法,以及一种在解码过程中可以输出更合适重复次数的重复评分方法。我们进行了自动和人工评估,包括将这些方法应用于预训练的语言模型T5以生成重复。实验结果表明,我们的方法在两个评估中都优于基线。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
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