Value type-the bridge to a better DST model

Abstract

Value type of the slots can provide lots of useful information for DST tasks. However, it has been ignored in most previous works. In this paper, we propose a new framework for DST task based on these value types. Firstly, we extract the type of token from each turn. Specifically, we divide the slots in the dataset into 9 categories according to the type of slot value, and then train a Ner model to extract the corresponding type-entity from each turn of conversation according to the token. Secondly, we improve the attention mode which is integrated into value type information between the slot and the conversation history to help each slot pay more attention to the turns that contain the same value type. Meanwhile, we introduce a sampling strategy to integrate these types into the attention formula, which decrease the error of Ner model. Finally, we conduct a comprehensive experiment on two multi-domain task-oriented conversation datasets, MultiWOZ 2.1 and MultiWOZ 2.4. The ablation experimental results show that our method is effective on both datasets, which verify the necessity of considering the type of slot value.

Publication
ACL 2023
Qixiang Gao
Qixiang Gao
Postgraduate Student

Task-oriented Dialogue System, Dialogue State Tracking

Yutao Mu
Yutao Mu
Postgraduate Student

Task-oriented Dialogue System, Spoken Language Understading

Chen Zeng
Chen Zeng
Postgraduate Student
Weiran Xu
Weiran Xu
Associate Professor, Master Supervisor, Ph.D Supervisor

Information Retrieval, Pattern Recognition, Machine Learning