@inproceedings{qixiang-etal-2023-value,
title = "Value type: the bridge to a better {DST} model",
author = "Qixiang, Gao and
Sun, Mingyang and
Mou, Yutao and
Zeng, Chen and
Xu, Weiran",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.78",
doi = "10.18653/v1/2023.findings-acl.78",
pages = "1211--1219",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qixiang-etal-2023-value">
<titleInfo>
<title>Value type: the bridge to a better DST model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gao</namePart>
<namePart type="family">Qixiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutao</namePart>
<namePart type="family">Mou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiran</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">qixiang-etal-2023-value</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.78</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.78</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1211</start>
<end>1219</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Value type: the bridge to a better DST model
%A Qixiang, Gao
%A Sun, Mingyang
%A Mou, Yutao
%A Zeng, Chen
%A Xu, Weiran
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F qixiang-etal-2023-value
%X 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.
%R 10.18653/v1/2023.findings-acl.78
%U https://aclanthology.org/2023.findings-acl.78
%U https://doi.org/10.18653/v1/2023.findings-acl.78
%P 1211-1219
Markdown (Informal)
[Value type: the bridge to a better DST model](https://aclanthology.org/2023.findings-acl.78) (Qixiang et al., Findings 2023)
ACL
- Gao Qixiang, Mingyang Sun, Yutao Mou, Chen Zeng, and Weiran Xu. 2023. Value type: the bridge to a better DST model. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1211–1219, Toronto, Canada. Association for Computational Linguistics.