@inproceedings{xiong-etal-2022-extreme,
title = "Extreme {Z}ero-{S}hot Learning for Extreme Text Classification",
author = "Xiong, Yuanhao and
Chang, Wei-Cheng and
Hsieh, Cho-Jui and
Yu, Hsiang-Fu and
Dhillon, Inderjit",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.399",
doi = "10.18653/v1/2022.naacl-main.399",
pages = "5455--5468",
abstract = "The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant labels for an input text instance from a large label set. However, the XMC setup faces two challenges: (1) it is not generalizable to predict unseen labels in dynamic environments, and (2) it requires a large amount of supervised (instance, label) pairs, which can be difficult to obtain for emerging domains. In this paper, we consider a more practical scenario called Extreme Zero-Shot XMC (EZ-XMC), in which no supervision is needed and merely raw text of instances and labels are accessible. Few-Shot XMC (FS-XMC), an extension to EZ-XMC with limited supervision is also investigated. To learn the semantic embeddings of instances and labels with raw text, we propose to pre-train Transformer-based encoders with self-supervised contrastive losses. Specifically, we develop a pre-training method $\textbf{MACLR}$, which thoroughly leverages the raw text with techniques including $\textbf{M}$ulti-scale $\textbf{A}$daptive $\textbf{C}$lustering, $\textbf{L}$abel $\textbf{R}$egularization, and self-training with pseudo positive pairs. Experimental results on four public EZ-XMC datasets demonstrate that MACLR achieves superior performance compared to all other leading baseline methods, in particular with approximately 5-10{\%} improvement in precision and recall on average. Moreover, we show that our pre-trained encoder can be further improved on FS-XMC when there are a limited number of ground-truth positive pairs in training. Our code is available at \url{https://github.com/amzn/pecos/tree/mainline/examples/MACLR}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiong-etal-2022-extreme">
<titleInfo>
<title>Extreme Zero-Shot Learning for Extreme Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanhao</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Cheng</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cho-Jui</namePart>
<namePart type="family">Hsieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsiang-Fu</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inderjit</namePart>
<namePart type="family">Dhillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant labels for an input text instance from a large label set. However, the XMC setup faces two challenges: (1) it is not generalizable to predict unseen labels in dynamic environments, and (2) it requires a large amount of supervised (instance, label) pairs, which can be difficult to obtain for emerging domains. In this paper, we consider a more practical scenario called Extreme Zero-Shot XMC (EZ-XMC), in which no supervision is needed and merely raw text of instances and labels are accessible. Few-Shot XMC (FS-XMC), an extension to EZ-XMC with limited supervision is also investigated. To learn the semantic embeddings of instances and labels with raw text, we propose to pre-train Transformer-based encoders with self-supervised contrastive losses. Specifically, we develop a pre-training method MACLR, which thoroughly leverages the raw text with techniques including Multi-scale Adaptive Clustering, Label Regularization, and self-training with pseudo positive pairs. Experimental results on four public EZ-XMC datasets demonstrate that MACLR achieves superior performance compared to all other leading baseline methods, in particular with approximately 5-10% improvement in precision and recall on average. Moreover, we show that our pre-trained encoder can be further improved on FS-XMC when there are a limited number of ground-truth positive pairs in training. Our code is available at https://github.com/amzn/pecos/tree/mainline/examples/MACLR.</abstract>
<identifier type="citekey">xiong-etal-2022-extreme</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.399</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.399</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>5455</start>
<end>5468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extreme Zero-Shot Learning for Extreme Text Classification
%A Xiong, Yuanhao
%A Chang, Wei-Cheng
%A Hsieh, Cho-Jui
%A Yu, Hsiang-Fu
%A Dhillon, Inderjit
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F xiong-etal-2022-extreme
%X The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant labels for an input text instance from a large label set. However, the XMC setup faces two challenges: (1) it is not generalizable to predict unseen labels in dynamic environments, and (2) it requires a large amount of supervised (instance, label) pairs, which can be difficult to obtain for emerging domains. In this paper, we consider a more practical scenario called Extreme Zero-Shot XMC (EZ-XMC), in which no supervision is needed and merely raw text of instances and labels are accessible. Few-Shot XMC (FS-XMC), an extension to EZ-XMC with limited supervision is also investigated. To learn the semantic embeddings of instances and labels with raw text, we propose to pre-train Transformer-based encoders with self-supervised contrastive losses. Specifically, we develop a pre-training method MACLR, which thoroughly leverages the raw text with techniques including Multi-scale Adaptive Clustering, Label Regularization, and self-training with pseudo positive pairs. Experimental results on four public EZ-XMC datasets demonstrate that MACLR achieves superior performance compared to all other leading baseline methods, in particular with approximately 5-10% improvement in precision and recall on average. Moreover, we show that our pre-trained encoder can be further improved on FS-XMC when there are a limited number of ground-truth positive pairs in training. Our code is available at https://github.com/amzn/pecos/tree/mainline/examples/MACLR.
%R 10.18653/v1/2022.naacl-main.399
%U https://aclanthology.org/2022.naacl-main.399
%U https://doi.org/10.18653/v1/2022.naacl-main.399
%P 5455-5468
Markdown (Informal)
[Extreme Zero-Shot Learning for Extreme Text Classification](https://aclanthology.org/2022.naacl-main.399) (Xiong et al., NAACL 2022)
ACL
- Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, and Inderjit Dhillon. 2022. Extreme Zero-Shot Learning for Extreme Text Classification. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5455–5468, Seattle, United States. Association for Computational Linguistics.