Dialogue State Tracking with Sparse Local Slot Attention

Longfei Yang, Jiyi Li, Sheng Li, T. Shinozaki
{"title":"Dialogue State Tracking with Sparse Local Slot Attention","authors":"Longfei Yang, Jiyi Li, Sheng Li, T. Shinozaki","doi":"10.18653/v1/2023.nlp4convai-1.4","DOIUrl":null,"url":null,"abstract":"Dialogue state tracking (DST) is designed to track the dialogue state during the conversations between users and systems, which is the core of task-oriented dialogue systems. Mainstream models predict the values for each slot with fully token-wise slot attention from dialogue history. However, such operations may result in overlooking the neighboring relationship. Moreover, it may lead the model to assign probability mass to irrelevant parts, while these parts contribute little. It becomes severe with the increase in dialogue length. Therefore, we investigate sparse local slot attention for DST in this work. Slot-specific local semantic information is obtained at a sub-sampled temporal resolution capturing local dependencies for each slot. Then these local representations are attended with sparse attention weights to guide the model to pay attention to relevant parts of local information for subsequent state value prediction. The experimental results on MultiWOZ 2.0 and 2.4 datasets show that the proposed approach effectively improves the performance of ontology-based dialogue state tracking, and performs better than token-wise attention for long dialogues.","PeriodicalId":169166,"journal":{"name":"Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2023.nlp4convai-1.4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Dialogue state tracking (DST) is designed to track the dialogue state during the conversations between users and systems, which is the core of task-oriented dialogue systems. Mainstream models predict the values for each slot with fully token-wise slot attention from dialogue history. However, such operations may result in overlooking the neighboring relationship. Moreover, it may lead the model to assign probability mass to irrelevant parts, while these parts contribute little. It becomes severe with the increase in dialogue length. Therefore, we investigate sparse local slot attention for DST in this work. Slot-specific local semantic information is obtained at a sub-sampled temporal resolution capturing local dependencies for each slot. Then these local representations are attended with sparse attention weights to guide the model to pay attention to relevant parts of local information for subsequent state value prediction. The experimental results on MultiWOZ 2.0 and 2.4 datasets show that the proposed approach effectively improves the performance of ontology-based dialogue state tracking, and performs better than token-wise attention for long dialogues.
稀疏局部时隙注意的对话状态跟踪
对话状态跟踪(DST)旨在跟踪用户与系统之间对话过程中的对话状态,是面向任务的对话系统的核心。主流模型预测每个插槽的值,并从对话历史中完全基于token的插槽关注。然而,这样的操作可能会导致忽略相邻关系。此外,它可能导致模型将概率质量分配给不相关的部分,而这些部分的贡献很小。随着对话长度的增加,它变得更加严重。因此,我们在这项工作中研究了DST的稀疏局部时隙关注。在捕获每个插槽的本地依赖关系的子采样时间分辨率下获得特定于插槽的本地语义信息。然后用稀疏的关注权来关注这些局部表示,引导模型关注局部信息的相关部分,以便进行后续的状态值预测。在MultiWOZ 2.0和2.4数据集上的实验结果表明,该方法有效地提高了基于本体的对话状态跟踪的性能,对于长对话的跟踪效果优于令牌关注。
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