@inproceedings{chen-etal-2024-overcoming,
title = "Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System",
author = "Chen, Chen and
Li, Ruizhe and
Hu, Yuchen and
Chen, Yuanyuan and
Qin, Chengwei and
Zhang, Qiang",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.5",
pages = "48--61",
abstract = "Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing user needs. However, catastrophic forgetting dramatically degrades the model performance in face of a long streamed curriculum. In this paper, we aim to overcome the forgetting problem in ToDs and propose a method (HESIT) with hyper-gradient-based exemplar strategy, which samples influential exemplars for periodic retraining. Instead of unilaterally observing data or models, HESIT adopts a profound exemplar selection strategy that considers the general performance of the trained model when selecting exemplars for each task domain. Specifically, HESIT analyzes the training data influence by tracing their hyper-gradient in the optimization process. Furthermore, HESIT avoids estimating Hessian to make it compatible for ToDs with a large pre-trained model. Experimental results show that HESIT effectively alleviates catastrophic forgetting by exemplar selection, and achieves state-of-the-art performance on the largest CL benchmark of ToDs in terms of all metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-overcoming">
<titleInfo>
<title>Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruizhe</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanyuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengwei</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing user needs. However, catastrophic forgetting dramatically degrades the model performance in face of a long streamed curriculum. In this paper, we aim to overcome the forgetting problem in ToDs and propose a method (HESIT) with hyper-gradient-based exemplar strategy, which samples influential exemplars for periodic retraining. Instead of unilaterally observing data or models, HESIT adopts a profound exemplar selection strategy that considers the general performance of the trained model when selecting exemplars for each task domain. Specifically, HESIT analyzes the training data influence by tracing their hyper-gradient in the optimization process. Furthermore, HESIT avoids estimating Hessian to make it compatible for ToDs with a large pre-trained model. Experimental results show that HESIT effectively alleviates catastrophic forgetting by exemplar selection, and achieves state-of-the-art performance on the largest CL benchmark of ToDs in terms of all metrics.</abstract>
<identifier type="citekey">chen-etal-2024-overcoming</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.5</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>48</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System
%A Chen, Chen
%A Li, Ruizhe
%A Hu, Yuchen
%A Chen, Yuanyuan
%A Qin, Chengwei
%A Zhang, Qiang
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F chen-etal-2024-overcoming
%X Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing user needs. However, catastrophic forgetting dramatically degrades the model performance in face of a long streamed curriculum. In this paper, we aim to overcome the forgetting problem in ToDs and propose a method (HESIT) with hyper-gradient-based exemplar strategy, which samples influential exemplars for periodic retraining. Instead of unilaterally observing data or models, HESIT adopts a profound exemplar selection strategy that considers the general performance of the trained model when selecting exemplars for each task domain. Specifically, HESIT analyzes the training data influence by tracing their hyper-gradient in the optimization process. Furthermore, HESIT avoids estimating Hessian to make it compatible for ToDs with a large pre-trained model. Experimental results show that HESIT effectively alleviates catastrophic forgetting by exemplar selection, and achieves state-of-the-art performance on the largest CL benchmark of ToDs in terms of all metrics.
%U https://aclanthology.org/2024.findings-acl.5
%P 48-61
Markdown (Informal)
[Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System](https://aclanthology.org/2024.findings-acl.5) (Chen et al., Findings 2024)
ACL