@inproceedings{tran-etal-2024-preserving,
title = "Preserving Generalization of Language models in Few-shot Continual Relation Extraction",
author = "Tran, Quyen and
Thanh, Nguyen and
Anh, Nguyen and
Hai, Nam and
Le, Trung and
Ngo, Linh and
Nguyen, Thien",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.763",
pages = "13771--13784",
abstract = "Few-shot Continual Relations Extraction (FCRE) is an emerging and dynamic area of study where models can sequentially integrate knowledge from new relations with limited labeled data while circumventing catastrophic forgetting and preserving prior knowledge from pre-trained backbones. In this work, we introduce a novel method that leverages often-discarded language model heads. By employing these components via a mutual information maximization strategy, our approach helps maintain prior knowledge from the pre-trained backbone and strategically aligns the primary classification head, thereby enhancing model performance. Furthermore, we explore the potential of Large Language Models (LLMs), renowned for their wealth of knowledge, in addressing FCRE challenges. Our comprehensive experimental results underscore the efficacy of the proposed method and offer valuable insights for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2024-preserving">
<titleInfo>
<title>Preserving Generalization of Language models in Few-shot Continual Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quyen</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="family">Thanh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="family">Anh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nam</namePart>
<namePart type="family">Hai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="family">Ngo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Few-shot Continual Relations Extraction (FCRE) is an emerging and dynamic area of study where models can sequentially integrate knowledge from new relations with limited labeled data while circumventing catastrophic forgetting and preserving prior knowledge from pre-trained backbones. In this work, we introduce a novel method that leverages often-discarded language model heads. By employing these components via a mutual information maximization strategy, our approach helps maintain prior knowledge from the pre-trained backbone and strategically aligns the primary classification head, thereby enhancing model performance. Furthermore, we explore the potential of Large Language Models (LLMs), renowned for their wealth of knowledge, in addressing FCRE challenges. Our comprehensive experimental results underscore the efficacy of the proposed method and offer valuable insights for future work.</abstract>
<identifier type="citekey">tran-etal-2024-preserving</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.763</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>13771</start>
<end>13784</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Preserving Generalization of Language models in Few-shot Continual Relation Extraction
%A Tran, Quyen
%A Thanh, Nguyen
%A Anh, Nguyen
%A Hai, Nam
%A Le, Trung
%A Ngo, Linh
%A Nguyen, Thien
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F tran-etal-2024-preserving
%X Few-shot Continual Relations Extraction (FCRE) is an emerging and dynamic area of study where models can sequentially integrate knowledge from new relations with limited labeled data while circumventing catastrophic forgetting and preserving prior knowledge from pre-trained backbones. In this work, we introduce a novel method that leverages often-discarded language model heads. By employing these components via a mutual information maximization strategy, our approach helps maintain prior knowledge from the pre-trained backbone and strategically aligns the primary classification head, thereby enhancing model performance. Furthermore, we explore the potential of Large Language Models (LLMs), renowned for their wealth of knowledge, in addressing FCRE challenges. Our comprehensive experimental results underscore the efficacy of the proposed method and offer valuable insights for future work.
%U https://aclanthology.org/2024.emnlp-main.763
%P 13771-13784
Markdown (Informal)
[Preserving Generalization of Language models in Few-shot Continual Relation Extraction](https://aclanthology.org/2024.emnlp-main.763) (Tran et al., EMNLP 2024)
ACL
- Quyen Tran, Nguyen Thanh, Nguyen Anh, Nam Hai, Trung Le, Linh Ngo, and Thien Nguyen. 2024. Preserving Generalization of Language models in Few-shot Continual Relation Extraction. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13771–13784, Miami, Florida, USA. Association for Computational Linguistics.