DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation

Chuan Meng, Pengjie Ren, Zhumin Chen, Weiwei Sun, Z. Ren, Zhaopeng Tu, M. de Rijke
{"title":"DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation","authors":"Chuan Meng, Pengjie Ren, Zhumin Chen, Weiwei Sun, Z. Ren, Zhaopeng Tu, M. de Rijke","doi":"10.1145/3397271.3401097","DOIUrl":null,"url":null,"abstract":"Today's conversational agents often generate responses that not sufficiently informative. One way of making them more informative is through the use of of external knowledge sources with so-called Knowledge-Grounded Conversations (KGCs). In this paper, we target the Knowledge Selection (KS) task, a key ingredient in KGC, that is aimed at selecting the appropriate knowledge to be used in the next response. Existing approaches to Knowledge Selection (KS) based on learned representations of the conversation context, that is previous conversation turns, and use Maximum Likelihood Estimation (MLE) to optimize KS. Such approaches have two main limitations. First, they do not explicitly track what knowledge has been used in the conversation nor how topics have shifted during the conversation. Second, MLE often relies on a limited set of example conversations for training, from which it is hard to infer that facts retrieved from the knowledge source can be re-used in multiple conversation contexts, and vice versa. We propose Dual Knowledge Interaction Network (DukeNet), a framework to address these challenges. DukeNet explicitly models knowledge tracking and knowledge shifting as dual tasks. We also design Dual Knowledge Interaction Learning (DukeL), an unsupervised learning scheme to train DukeNet by facilitating interactions between knowledge tracking and knowledge shifting, which, in turn, enables DukeNet to explore extra knowledge besides the knowledge encountered in the training set. This dual process also allows us to define rewards that help us to optimize both knowledge tracking and knowledge shifting. Experimental results on two public KGC benchmarks show that DukeNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that DukeNet enhanced by DukeL can select more appropriate knowledge and hence generate more informative and engaging responses.","PeriodicalId":252050,"journal":{"name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"48","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3397271.3401097","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 48

Abstract

Today's conversational agents often generate responses that not sufficiently informative. One way of making them more informative is through the use of of external knowledge sources with so-called Knowledge-Grounded Conversations (KGCs). In this paper, we target the Knowledge Selection (KS) task, a key ingredient in KGC, that is aimed at selecting the appropriate knowledge to be used in the next response. Existing approaches to Knowledge Selection (KS) based on learned representations of the conversation context, that is previous conversation turns, and use Maximum Likelihood Estimation (MLE) to optimize KS. Such approaches have two main limitations. First, they do not explicitly track what knowledge has been used in the conversation nor how topics have shifted during the conversation. Second, MLE often relies on a limited set of example conversations for training, from which it is hard to infer that facts retrieved from the knowledge source can be re-used in multiple conversation contexts, and vice versa. We propose Dual Knowledge Interaction Network (DukeNet), a framework to address these challenges. DukeNet explicitly models knowledge tracking and knowledge shifting as dual tasks. We also design Dual Knowledge Interaction Learning (DukeL), an unsupervised learning scheme to train DukeNet by facilitating interactions between knowledge tracking and knowledge shifting, which, in turn, enables DukeNet to explore extra knowledge besides the knowledge encountered in the training set. This dual process also allows us to define rewards that help us to optimize both knowledge tracking and knowledge shifting. Experimental results on two public KGC benchmarks show that DukeNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that DukeNet enhanced by DukeL can select more appropriate knowledge and hence generate more informative and engaging responses.
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
DukeNet:基于知识对话的双重知识交互网络
今天的会话代理通常会产生信息不足的响应。一种使它们更具信息性的方法是通过使用所谓的基于知识的对话(kgc)的外部知识来源。在本文中,我们的目标是知识选择(KS)任务,这是KGC的一个关键组成部分,旨在选择在下一个回答中使用的适当知识。现有的知识选择方法基于学习到的会话上下文表示,即先前的会话回合,并使用最大似然估计(MLE)来优化知识选择。这种方法有两个主要的局限性。首先,它们没有明确地跟踪谈话中使用了哪些知识,也没有跟踪谈话中话题是如何转移的。其次,MLE通常依赖于一组有限的示例对话进行训练,从中很难推断出从知识来源检索到的事实可以在多个对话上下文中重用,反之亦然。我们提出双知识交互网络(DukeNet),这是一个解决这些挑战的框架。DukeNet明确地将知识跟踪和知识转移建模为双重任务。我们还设计了双知识交互学习(Dual Knowledge Interaction Learning, DukeL),这是一种无监督学习方案,通过促进知识跟踪和知识转移之间的交互来训练DukeNet,从而使DukeNet能够探索除训练集中遇到的知识之外的额外知识。这种双重过程还允许我们定义奖励,帮助我们优化知识跟踪和知识转移。在两个公共KGC基准测试上的实验结果表明,DukeNet在自动和人工评估方面都明显优于最先进的方法,这表明DukeL增强的DukeNet可以选择更合适的知识,从而产生更丰富、更有吸引力的响应。
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
自引率
0.00%
发文量
0
期刊最新文献
MHM: Multi-modal Clinical Data based Hierarchical Multi-label Diagnosis Prediction Correlated Features Synthesis and Alignment for Zero-shot Cross-modal Retrieval DVGAN Models Versus Satisfaction: Towards a Better Understanding of Evaluation Metrics Global Context Enhanced Graph Neural Networks for Session-based Recommendation
×
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