@inproceedings{zhang-etal-2022-structural-contrastive,
title = "Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification",
author = "Zhang, Tianyi and
Xu, Zhaozhuo and
Medini, Tharun and
Shrivastava, Anshumali",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.362",
doi = "10.18653/v1/2022.findings-emnlp.362",
pages = "4937--4947",
abstract = "Zero-shot multi-label text classification (ZMTC) is a fundamental task in natural language processing with applications in the cold start problem of recommendation systems. Ideally, one would learn an expressive representation of both input text and label features so that ZMTC is transformed into a nearest neighbor search problem. However, the existing representation learning approaches for ZMTC struggle with accuracy as well as poor training efficiency. Firstly, the input text is structural, consisting of both short title sentences and long content paragraphs. It is challenging to model the correlation between short label descriptions and long structural input documents. Secondly, the enormous label space in ZMTC forces the existing approaches to perform multi-stage learning with label engineering. As a result, the training overhead is significant. In this paper, we address both problems by introducing an end-to-end structural contrastive representation learning approach. We propose a randomized text segmentation (RTS) technique to generate high-quality contrastive pairs. This RTS technique allows us to model title-content correlation. Additionally, we simplify the multi-stage ZMTC learning strategy by avoiding label engineering. Extensive experiments demonstrate that our approach leads to up to 2.33{\%} improvement in precision@1 and 5.94x speedup in training time on publicly available datasets. Our code is available publicly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-structural-contrastive">
<titleInfo>
<title>Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaozhuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharun</namePart>
<namePart type="family">Medini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anshumali</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-shot multi-label text classification (ZMTC) is a fundamental task in natural language processing with applications in the cold start problem of recommendation systems. Ideally, one would learn an expressive representation of both input text and label features so that ZMTC is transformed into a nearest neighbor search problem. However, the existing representation learning approaches for ZMTC struggle with accuracy as well as poor training efficiency. Firstly, the input text is structural, consisting of both short title sentences and long content paragraphs. It is challenging to model the correlation between short label descriptions and long structural input documents. Secondly, the enormous label space in ZMTC forces the existing approaches to perform multi-stage learning with label engineering. As a result, the training overhead is significant. In this paper, we address both problems by introducing an end-to-end structural contrastive representation learning approach. We propose a randomized text segmentation (RTS) technique to generate high-quality contrastive pairs. This RTS technique allows us to model title-content correlation. Additionally, we simplify the multi-stage ZMTC learning strategy by avoiding label engineering. Extensive experiments demonstrate that our approach leads to up to 2.33% improvement in precision@1 and 5.94x speedup in training time on publicly available datasets. Our code is available publicly.</abstract>
<identifier type="citekey">zhang-etal-2022-structural-contrastive</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.362</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.362</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4937</start>
<end>4947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification
%A Zhang, Tianyi
%A Xu, Zhaozhuo
%A Medini, Tharun
%A Shrivastava, Anshumali
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhang-etal-2022-structural-contrastive
%X Zero-shot multi-label text classification (ZMTC) is a fundamental task in natural language processing with applications in the cold start problem of recommendation systems. Ideally, one would learn an expressive representation of both input text and label features so that ZMTC is transformed into a nearest neighbor search problem. However, the existing representation learning approaches for ZMTC struggle with accuracy as well as poor training efficiency. Firstly, the input text is structural, consisting of both short title sentences and long content paragraphs. It is challenging to model the correlation between short label descriptions and long structural input documents. Secondly, the enormous label space in ZMTC forces the existing approaches to perform multi-stage learning with label engineering. As a result, the training overhead is significant. In this paper, we address both problems by introducing an end-to-end structural contrastive representation learning approach. We propose a randomized text segmentation (RTS) technique to generate high-quality contrastive pairs. This RTS technique allows us to model title-content correlation. Additionally, we simplify the multi-stage ZMTC learning strategy by avoiding label engineering. Extensive experiments demonstrate that our approach leads to up to 2.33% improvement in precision@1 and 5.94x speedup in training time on publicly available datasets. Our code is available publicly.
%R 10.18653/v1/2022.findings-emnlp.362
%U https://aclanthology.org/2022.findings-emnlp.362
%U https://doi.org/10.18653/v1/2022.findings-emnlp.362
%P 4937-4947
Markdown (Informal)
[Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification](https://aclanthology.org/2022.findings-emnlp.362) (Zhang et al., Findings 2022)
ACL