@inproceedings{wang-etal-2022-shot,
title = "Few-Shot Class-Incremental Learning for Named Entity Recognition",
author = "Wang, Rui and
Yu, Tong and
Zhao, Handong and
Kim, Sungchul and
Mitra, Subrata and
Zhang, Ruiyi and
Henao, Ricardo",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.43",
doi = "10.18653/v1/2022.acl-long.43",
pages = "571--582",
abstract = "Previous work of class-incremental learning for Named Entity Recognition (NER) relies on the assumption that there exists abundance of labeled data for the training of new classes. In this work, we study a more challenging but practical problem, \textit{i.e.}, few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones. To alleviate the problem of catastrophic forgetting in few-shot class-incremental learning, we reconstruct synthetic training data of the old classes using the trained NER model, augmenting the training of new classes. We further develop a framework that distills from the existing model with both synthetic data, and real data from the current training set. Experimental results show that our approach achieves significant improvements over existing baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-shot">
<titleInfo>
<title>Few-Shot Class-Incremental Learning for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Handong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungchul</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subrata</namePart>
<namePart type="family">Mitra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Henao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work of class-incremental learning for Named Entity Recognition (NER) relies on the assumption that there exists abundance of labeled data for the training of new classes. In this work, we study a more challenging but practical problem, i.e., few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones. To alleviate the problem of catastrophic forgetting in few-shot class-incremental learning, we reconstruct synthetic training data of the old classes using the trained NER model, augmenting the training of new classes. We further develop a framework that distills from the existing model with both synthetic data, and real data from the current training set. Experimental results show that our approach achieves significant improvements over existing baselines.</abstract>
<identifier type="citekey">wang-etal-2022-shot</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.43</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.43</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>571</start>
<end>582</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-Shot Class-Incremental Learning for Named Entity Recognition
%A Wang, Rui
%A Yu, Tong
%A Zhao, Handong
%A Kim, Sungchul
%A Mitra, Subrata
%A Zhang, Ruiyi
%A Henao, Ricardo
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F wang-etal-2022-shot
%X Previous work of class-incremental learning for Named Entity Recognition (NER) relies on the assumption that there exists abundance of labeled data for the training of new classes. In this work, we study a more challenging but practical problem, i.e., few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones. To alleviate the problem of catastrophic forgetting in few-shot class-incremental learning, we reconstruct synthetic training data of the old classes using the trained NER model, augmenting the training of new classes. We further develop a framework that distills from the existing model with both synthetic data, and real data from the current training set. Experimental results show that our approach achieves significant improvements over existing baselines.
%R 10.18653/v1/2022.acl-long.43
%U https://aclanthology.org/2022.acl-long.43
%U https://doi.org/10.18653/v1/2022.acl-long.43
%P 571-582
Markdown (Informal)
[Few-Shot Class-Incremental Learning for Named Entity Recognition](https://aclanthology.org/2022.acl-long.43) (Wang et al., ACL 2022)
ACL
- Rui Wang, Tong Yu, Handong Zhao, Sungchul Kim, Subrata Mitra, Ruiyi Zhang, and Ricardo Henao. 2022. Few-Shot Class-Incremental Learning for Named Entity Recognition. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 571–582, Dublin, Ireland. Association for Computational Linguistics.