@article{chen-etal-2024-retrieval-style,
title = "Retrieval-style In-context Learning for Few-shot Hierarchical Text Classification",
author = "Chen, Huiyao and
Zhao, Yu and
Chen, Zulong and
Wang, Mengjia and
Li, Liangyue and
Zhang, Meishan and
Zhang, Min",
journal = "Transactions of the Association for Computational Linguistics",
volume = "12",
year = "2024",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2024.tacl-1.67",
doi = "10.1162/tacl_a_00697",
pages = "1214--1231",
abstract = "Hierarchical text classification (HTC) is an important task with broad applications, and few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Particularly, we equip the retrieval database with HTC label-aware representations for the input texts, which is achieved by continual training on a pretrained language model with masked language modeling (MLM), layer-wise classification (CLS, specifically for HTC), and a novel divergent contrastive learning (DCL, mainly for adjacent semantically similar labels) objective. Experimental results on three benchmark datasets demonstrate superior performance of our method, and we can achieve state-of-the-art results in few-shot HTC.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-retrieval-style">
<titleInfo>
<title>Retrieval-style In-context Learning for Few-shot Hierarchical Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huiyao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zulong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengjia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangyue</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meishan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Hierarchical text classification (HTC) is an important task with broad applications, and few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Particularly, we equip the retrieval database with HTC label-aware representations for the input texts, which is achieved by continual training on a pretrained language model with masked language modeling (MLM), layer-wise classification (CLS, specifically for HTC), and a novel divergent contrastive learning (DCL, mainly for adjacent semantically similar labels) objective. Experimental results on three benchmark datasets demonstrate superior performance of our method, and we can achieve state-of-the-art results in few-shot HTC.</abstract>
<identifier type="citekey">chen-etal-2024-retrieval-style</identifier>
<identifier type="doi">10.1162/tacl_a_00697</identifier>
<location>
<url>https://aclanthology.org/2024.tacl-1.67</url>
</location>
<part>
<date>2024</date>
<detail type="volume"><number>12</number></detail>
<extent unit="page">
<start>1214</start>
<end>1231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Retrieval-style In-context Learning for Few-shot Hierarchical Text Classification
%A Chen, Huiyao
%A Zhao, Yu
%A Chen, Zulong
%A Wang, Mengjia
%A Li, Liangyue
%A Zhang, Meishan
%A Zhang, Min
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F chen-etal-2024-retrieval-style
%X Hierarchical text classification (HTC) is an important task with broad applications, and few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Particularly, we equip the retrieval database with HTC label-aware representations for the input texts, which is achieved by continual training on a pretrained language model with masked language modeling (MLM), layer-wise classification (CLS, specifically for HTC), and a novel divergent contrastive learning (DCL, mainly for adjacent semantically similar labels) objective. Experimental results on three benchmark datasets demonstrate superior performance of our method, and we can achieve state-of-the-art results in few-shot HTC.
%R 10.1162/tacl_a_00697
%U https://aclanthology.org/2024.tacl-1.67
%U https://doi.org/10.1162/tacl_a_00697
%P 1214-1231
Markdown (Informal)
[Retrieval-style In-context Learning for Few-shot Hierarchical Text Classification](https://aclanthology.org/2024.tacl-1.67) (Chen et al., TACL 2024)
ACL