@inproceedings{zhang-etal-2022-learn,
title = "Learn to Adapt for Generalized Zero-Shot Text Classification",
author = "Zhang, Yiwen and
Yuan, Caixia and
Wang, Xiaojie and
Bai, Ziwei and
Liu, Yongbin",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.39",
doi = "10.18653/v1/2022.acl-long.39",
pages = "517--527",
abstract = "Generalized zero-shot text classification aims to classify textual instances from both previously seen classes and incrementally emerging unseen classes. Most existing methods generalize poorly since the learned parameters are only optimal for seen classes rather than for both classes, and the parameters keep stationary in predicting procedures. To address these challenges, we propose a novel Learn to Adapt (LTA) network using a variant meta-learning framework. Specifically, LTA trains an adaptive classifier by using both seen and virtual unseen classes to simulate a generalized zero-shot learning (GZSL) scenario in accordance with the test time, and simultaneously learns to calibrate the class prototypes and sample representations to make the learned parameters adaptive to incoming unseen classes. We claim that the proposed model is capable of representing all prototypes and samples from both classes to a more consistent distribution in a global space. Extensive experiments on five text classification datasets show that our model outperforms several competitive previous approaches by large margins. The code and the whole datasets are available at \url{https://github.com/Quareia/LTA}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-learn">
<titleInfo>
<title>Learn to Adapt for Generalized Zero-Shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiwen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caixia</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongbin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generalized zero-shot text classification aims to classify textual instances from both previously seen classes and incrementally emerging unseen classes. Most existing methods generalize poorly since the learned parameters are only optimal for seen classes rather than for both classes, and the parameters keep stationary in predicting procedures. To address these challenges, we propose a novel Learn to Adapt (LTA) network using a variant meta-learning framework. Specifically, LTA trains an adaptive classifier by using both seen and virtual unseen classes to simulate a generalized zero-shot learning (GZSL) scenario in accordance with the test time, and simultaneously learns to calibrate the class prototypes and sample representations to make the learned parameters adaptive to incoming unseen classes. We claim that the proposed model is capable of representing all prototypes and samples from both classes to a more consistent distribution in a global space. Extensive experiments on five text classification datasets show that our model outperforms several competitive previous approaches by large margins. The code and the whole datasets are available at https://github.com/Quareia/LTA.</abstract>
<identifier type="citekey">zhang-etal-2022-learn</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.39</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.39</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>517</start>
<end>527</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learn to Adapt for Generalized Zero-Shot Text Classification
%A Zhang, Yiwen
%A Yuan, Caixia
%A Wang, Xiaojie
%A Bai, Ziwei
%A Liu, Yongbin
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F zhang-etal-2022-learn
%X Generalized zero-shot text classification aims to classify textual instances from both previously seen classes and incrementally emerging unseen classes. Most existing methods generalize poorly since the learned parameters are only optimal for seen classes rather than for both classes, and the parameters keep stationary in predicting procedures. To address these challenges, we propose a novel Learn to Adapt (LTA) network using a variant meta-learning framework. Specifically, LTA trains an adaptive classifier by using both seen and virtual unseen classes to simulate a generalized zero-shot learning (GZSL) scenario in accordance with the test time, and simultaneously learns to calibrate the class prototypes and sample representations to make the learned parameters adaptive to incoming unseen classes. We claim that the proposed model is capable of representing all prototypes and samples from both classes to a more consistent distribution in a global space. Extensive experiments on five text classification datasets show that our model outperforms several competitive previous approaches by large margins. The code and the whole datasets are available at https://github.com/Quareia/LTA.
%R 10.18653/v1/2022.acl-long.39
%U https://aclanthology.org/2022.acl-long.39
%U https://doi.org/10.18653/v1/2022.acl-long.39
%P 517-527
Markdown (Informal)
[Learn to Adapt for Generalized Zero-Shot Text Classification](https://aclanthology.org/2022.acl-long.39) (Zhang et al., ACL 2022)
ACL
- Yiwen Zhang, Caixia Yuan, Xiaojie Wang, Ziwei Bai, and Yongbin Liu. 2022. Learn to Adapt for Generalized Zero-Shot Text Classification. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 517–527, Dublin, Ireland. Association for Computational Linguistics.