Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery

IF 4.2 1区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Transactions of the Association for Computational Linguistics Pub Date : 2023-03-02 DOI:10.1162/tacl_a_00561
Tao Feng, Lizhen Qu, Gholamreza Haffari
{"title":"Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery","authors":"Tao Feng, Lizhen Qu, Gholamreza Haffari","doi":"10.1162/tacl_a_00561","DOIUrl":null,"url":null,"abstract":"In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDialog curated by ourselves. The current models indeed suffer from spurious correlations and have a tendency to generate irrelevant and generic responses. Inspired by causal discovery algorithms, we propose a novel model-agnostic method for training and inference using a conditional independence classifier. The classifier is trained by a constrained self-training method, coined ConSTrain, to overcome data sparsity. The experimental results based on both human and automatic evaluation show that our method significantly outperforms the competitive baselines in terms of relevance, informativeness, and fluency.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"511-530"},"PeriodicalIF":4.2000,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions of the Association for Computational Linguistics","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1162/tacl_a_00561","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDialog curated by ourselves. The current models indeed suffer from spurious correlations and have a tendency to generate irrelevant and generic responses. Inspired by causal discovery algorithms, we propose a novel model-agnostic method for training and inference using a conditional independence classifier. The classifier is trained by a constrained self-training method, coined ConSTrain, to overcome data sparsity. The experimental results based on both human and automatic evaluation show that our method significantly outperforms the competitive baselines in terms of relevance, informativeness, and fluency.
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
少即是多:通过因果发现减轻开放域对话响应生成模型的虚假关联
在本文中,我们首次基于自己策划的语料库CGDialog对开放域响应生成模型的虚假相关性进行了研究。目前的模型确实存在虚假的相关性,并有产生不相关和通用反应的趋势。受因果发现算法的启发,我们提出了一种新的模型不可知方法,用于使用条件独立分类器进行训练和推理。分类器通过一种被称为ConSTrain的约束自训练方法来训练,以克服数据稀疏性。基于人工和自动评估的实验结果表明,我们的方法在相关性、信息性和流畅性方面显著优于竞争基线。
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 去求助
来源期刊
CiteScore
32.60
自引率
4.60%
发文量
58
审稿时长
8 weeks
期刊介绍: The highly regarded quarterly journal Computational Linguistics has a companion journal called Transactions of the Association for Computational Linguistics. This open access journal publishes articles in all areas of natural language processing and is an important resource for academic and industry computational linguists, natural language processing experts, artificial intelligence and machine learning investigators, cognitive scientists, speech specialists, as well as linguists and philosophers. The journal disseminates work of vital relevance to these professionals on an annual basis.
期刊最新文献
General then Personal: Decoupling and Pre-training for Personalized Headline Generation MissModal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations An Efficient Self-Supervised Cross-View Training For Sentence Embedding
×
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