@inproceedings{yu-etal-2024-flexible,
title = "Flexible Weight Tuning and Weight Fusion Strategies for Continual Named Entity Recognition",
author = "Yu, Yahan and
Zhang, Duzhen and
Chen, Xiuyi and
Chu, Chenhui",
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.79",
pages = "1351--1358",
abstract = "Continual Named Entity Recognition (CNER) is dedicated to sequentially learning new entity types while mitigating catastrophic forgetting of old entity types. Traditional CNER approaches commonly employ knowledge distillation to retain old knowledge within the current model. However, because only the representations of old and new models are constrained to be consistent, the reliance solely on distillation in existing methods still suffers from catastrophic forgetting. To further alleviate the forgetting issue of old entity types, this paper introduces flexible Weight Tuning (WT) and Weight Fusion (WF) strategies for CNER. The WT strategy, applied at each training step, employs a learning rate schedule on the parameters of the current model. After learning the current task, the WF strategy dynamically integrates knowledge from both the current and previous models for inference. Notably, these two strategies are model-agnostic and seamlessly integrate with existing State-Of-The-Art (SOTA) models. Extensive experiments demonstrate that the WT and WF strategies consistently enhance the performance of previous SOTA methods across ten CNER settings in three datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2024-flexible">
<titleInfo>
<title>Flexible Weight Tuning and Weight Fusion Strategies for Continual Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yahan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duzhen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</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>Continual Named Entity Recognition (CNER) is dedicated to sequentially learning new entity types while mitigating catastrophic forgetting of old entity types. Traditional CNER approaches commonly employ knowledge distillation to retain old knowledge within the current model. However, because only the representations of old and new models are constrained to be consistent, the reliance solely on distillation in existing methods still suffers from catastrophic forgetting. To further alleviate the forgetting issue of old entity types, this paper introduces flexible Weight Tuning (WT) and Weight Fusion (WF) strategies for CNER. The WT strategy, applied at each training step, employs a learning rate schedule on the parameters of the current model. After learning the current task, the WF strategy dynamically integrates knowledge from both the current and previous models for inference. Notably, these two strategies are model-agnostic and seamlessly integrate with existing State-Of-The-Art (SOTA) models. Extensive experiments demonstrate that the WT and WF strategies consistently enhance the performance of previous SOTA methods across ten CNER settings in three datasets.</abstract>
<identifier type="citekey">yu-etal-2024-flexible</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.79</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1351</start>
<end>1358</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Flexible Weight Tuning and Weight Fusion Strategies for Continual Named Entity Recognition
%A Yu, Yahan
%A Zhang, Duzhen
%A Chen, Xiuyi
%A Chu, Chenhui
%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 yu-etal-2024-flexible
%X Continual Named Entity Recognition (CNER) is dedicated to sequentially learning new entity types while mitigating catastrophic forgetting of old entity types. Traditional CNER approaches commonly employ knowledge distillation to retain old knowledge within the current model. However, because only the representations of old and new models are constrained to be consistent, the reliance solely on distillation in existing methods still suffers from catastrophic forgetting. To further alleviate the forgetting issue of old entity types, this paper introduces flexible Weight Tuning (WT) and Weight Fusion (WF) strategies for CNER. The WT strategy, applied at each training step, employs a learning rate schedule on the parameters of the current model. After learning the current task, the WF strategy dynamically integrates knowledge from both the current and previous models for inference. Notably, these two strategies are model-agnostic and seamlessly integrate with existing State-Of-The-Art (SOTA) models. Extensive experiments demonstrate that the WT and WF strategies consistently enhance the performance of previous SOTA methods across ten CNER settings in three datasets.
%U https://aclanthology.org/2024.findings-acl.79
%P 1351-1358
Markdown (Informal)
[Flexible Weight Tuning and Weight Fusion Strategies for Continual Named Entity Recognition](https://aclanthology.org/2024.findings-acl.79) (Yu et al., Findings 2024)
ACL