@inproceedings{wang-xin-2022-stop,
title = "How to Stop an Avalanche? {J}o{D}e{M}: Joint Decision Making through Compare and Contrast for Dialog State Tracking",
author = "Wang, Haoming and
Xin, Wang",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.521",
doi = "10.18653/v1/2022.findings-emnlp.521",
pages = "7030--7041",
abstract = "Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing state-of-the-art DST model incorporates insight and intuition from the human experience into design of supplementary labels, which greatly assisted the training process of turn-by-turn DST model. Though the turn-by-turn scheme and supplementary labels enabled satisfactory performance on the task, most of the DST models of this fashion label or process the raw dialogue data on the premise that the last turn dialogue state is always correct, which is usually not the case. In this paper, we address the negative impact resulted from the premise above as the avalanche phenomenon. After that, we propose JoDeM, a state-of-the-art DST model which can tackle the Avalanche phenomenon with two mechanisms. First mechanism is a jointly decision making method to extract key information from the dialogue. Second mechanism is a compare and contrast dialogue update technique to prevent error accumulation. Example study and graph analysis are presented to support our claim about the harmfulness of avalanche phenomenon. We also conduct quantitative and qualitative experiments on the high quality MultiWOZ2.3 corpus dataset to demonstrate that the proposed model not only outperforms the existing state-of-the-art methods, but also proves the validity of solving avalanche degradation problem.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-xin-2022-stop">
<titleInfo>
<title>How to Stop an Avalanche? JoDeM: Joint Decision Making through Compare and Contrast for Dialog State Tracking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoming</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Xin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing state-of-the-art DST model incorporates insight and intuition from the human experience into design of supplementary labels, which greatly assisted the training process of turn-by-turn DST model. Though the turn-by-turn scheme and supplementary labels enabled satisfactory performance on the task, most of the DST models of this fashion label or process the raw dialogue data on the premise that the last turn dialogue state is always correct, which is usually not the case. In this paper, we address the negative impact resulted from the premise above as the avalanche phenomenon. After that, we propose JoDeM, a state-of-the-art DST model which can tackle the Avalanche phenomenon with two mechanisms. First mechanism is a jointly decision making method to extract key information from the dialogue. Second mechanism is a compare and contrast dialogue update technique to prevent error accumulation. Example study and graph analysis are presented to support our claim about the harmfulness of avalanche phenomenon. We also conduct quantitative and qualitative experiments on the high quality MultiWOZ2.3 corpus dataset to demonstrate that the proposed model not only outperforms the existing state-of-the-art methods, but also proves the validity of solving avalanche degradation problem.</abstract>
<identifier type="citekey">wang-xin-2022-stop</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.521</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.521</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7030</start>
<end>7041</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Stop an Avalanche? JoDeM: Joint Decision Making through Compare and Contrast for Dialog State Tracking
%A Wang, Haoming
%A Xin, Wang
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wang-xin-2022-stop
%X Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing state-of-the-art DST model incorporates insight and intuition from the human experience into design of supplementary labels, which greatly assisted the training process of turn-by-turn DST model. Though the turn-by-turn scheme and supplementary labels enabled satisfactory performance on the task, most of the DST models of this fashion label or process the raw dialogue data on the premise that the last turn dialogue state is always correct, which is usually not the case. In this paper, we address the negative impact resulted from the premise above as the avalanche phenomenon. After that, we propose JoDeM, a state-of-the-art DST model which can tackle the Avalanche phenomenon with two mechanisms. First mechanism is a jointly decision making method to extract key information from the dialogue. Second mechanism is a compare and contrast dialogue update technique to prevent error accumulation. Example study and graph analysis are presented to support our claim about the harmfulness of avalanche phenomenon. We also conduct quantitative and qualitative experiments on the high quality MultiWOZ2.3 corpus dataset to demonstrate that the proposed model not only outperforms the existing state-of-the-art methods, but also proves the validity of solving avalanche degradation problem.
%R 10.18653/v1/2022.findings-emnlp.521
%U https://aclanthology.org/2022.findings-emnlp.521
%U https://doi.org/10.18653/v1/2022.findings-emnlp.521
%P 7030-7041
Markdown (Informal)
[How to Stop an Avalanche? JoDeM: Joint Decision Making through Compare and Contrast for Dialog State Tracking](https://aclanthology.org/2022.findings-emnlp.521) (Wang & Xin, Findings 2022)
ACL