@inproceedings{cao-zhang-2022-otseq2set,
title = "{OTS}eq2{S}et: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification",
author = "Cao, Jie and
Zhang, Yin",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.377",
doi = "10.18653/v1/2022.emnlp-main.377",
pages = "5588--5597",
abstract = "Extreme multi-label text classification (XMTC) is the task of finding the most relevant subset labels from an extremely large-scale label collection. Recently, some deep learning models have achieved state-of-the-art results in XMTC tasks. These models commonly predict scores for all labels by a fully connected layer as the last layer of the model. However, such models can{'}t predict a relatively complete and variable-length label subset for each document, because they select positive labels relevant to the document by a fixed threshold or take top k labels in descending order of scores. A less popular type of deep learning models called sequence-to-sequence (Seq2Seq) focus on predicting variable-length positive labels in sequence style. However, the labels in XMTC tasks are essentially an unordered set rather than an ordered sequence, the default order of labels restrains Seq2Seq models in training. To address this limitation in Seq2Seq, we propose an autoregressive sequence-to-set model for XMTC tasks named OTSeq2Set. Our model generates predictions in student-forcing scheme and is trained by a loss function based on bipartite matching which enables permutation-invariance. Meanwhile, we use the optimal transport distance as a measurement to force the model to focus on the closest labels in semantic label space. Experiments show that OTSeq2Set outperforms other competitive baselines on 4 benchmark datasets. Especially, on the Wikipedia dataset with 31k labels, it outperforms the state-of-the-art Seq2Seq method by 16.34{\%} in micro-F1 score. The code is available at https://github.com/caojie54/OTSeq2Set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-zhang-2022-otseq2set">
<titleInfo>
<title>OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="family">Zhang</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>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</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>Extreme multi-label text classification (XMTC) is the task of finding the most relevant subset labels from an extremely large-scale label collection. Recently, some deep learning models have achieved state-of-the-art results in XMTC tasks. These models commonly predict scores for all labels by a fully connected layer as the last layer of the model. However, such models can’t predict a relatively complete and variable-length label subset for each document, because they select positive labels relevant to the document by a fixed threshold or take top k labels in descending order of scores. A less popular type of deep learning models called sequence-to-sequence (Seq2Seq) focus on predicting variable-length positive labels in sequence style. However, the labels in XMTC tasks are essentially an unordered set rather than an ordered sequence, the default order of labels restrains Seq2Seq models in training. To address this limitation in Seq2Seq, we propose an autoregressive sequence-to-set model for XMTC tasks named OTSeq2Set. Our model generates predictions in student-forcing scheme and is trained by a loss function based on bipartite matching which enables permutation-invariance. Meanwhile, we use the optimal transport distance as a measurement to force the model to focus on the closest labels in semantic label space. Experiments show that OTSeq2Set outperforms other competitive baselines on 4 benchmark datasets. Especially, on the Wikipedia dataset with 31k labels, it outperforms the state-of-the-art Seq2Seq method by 16.34% in micro-F1 score. The code is available at https://github.com/caojie54/OTSeq2Set.</abstract>
<identifier type="citekey">cao-zhang-2022-otseq2set</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.377</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.377</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5588</start>
<end>5597</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification
%A Cao, Jie
%A Zhang, Yin
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F cao-zhang-2022-otseq2set
%X Extreme multi-label text classification (XMTC) is the task of finding the most relevant subset labels from an extremely large-scale label collection. Recently, some deep learning models have achieved state-of-the-art results in XMTC tasks. These models commonly predict scores for all labels by a fully connected layer as the last layer of the model. However, such models can’t predict a relatively complete and variable-length label subset for each document, because they select positive labels relevant to the document by a fixed threshold or take top k labels in descending order of scores. A less popular type of deep learning models called sequence-to-sequence (Seq2Seq) focus on predicting variable-length positive labels in sequence style. However, the labels in XMTC tasks are essentially an unordered set rather than an ordered sequence, the default order of labels restrains Seq2Seq models in training. To address this limitation in Seq2Seq, we propose an autoregressive sequence-to-set model for XMTC tasks named OTSeq2Set. Our model generates predictions in student-forcing scheme and is trained by a loss function based on bipartite matching which enables permutation-invariance. Meanwhile, we use the optimal transport distance as a measurement to force the model to focus on the closest labels in semantic label space. Experiments show that OTSeq2Set outperforms other competitive baselines on 4 benchmark datasets. Especially, on the Wikipedia dataset with 31k labels, it outperforms the state-of-the-art Seq2Seq method by 16.34% in micro-F1 score. The code is available at https://github.com/caojie54/OTSeq2Set.
%R 10.18653/v1/2022.emnlp-main.377
%U https://aclanthology.org/2022.emnlp-main.377
%U https://doi.org/10.18653/v1/2022.emnlp-main.377
%P 5588-5597
Markdown (Informal)
[OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification](https://aclanthology.org/2022.emnlp-main.377) (Cao & Zhang, EMNLP 2022)
ACL