@inproceedings{liu-etal-2023-zero,
title = "Zero-Shot Text Classification via Self-Supervised Tuning",
author = "Liu, Chaoqun and
Zhang, Wenxuan and
Chen, Guizhen and
Wu, Xiaobao and
Luu, Anh Tuan and
Chang, Chip Hong and
Bing, Lidong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.110/",
doi = "10.18653/v1/2023.findings-acl.110",
pages = "1743--1761",
abstract = "Existing solutions to zero-shot text classification either conduct prompting with pre-trained language models, which is sensitive to the choices of templates, or rely on large-scale annotated data of relevant tasks for meta-tuning. In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning. By exploring the inherent structure of free texts, we propose a new learning objective called first sentence prediction to bridge the gap between unlabeled data and text classification tasks. After tuning the model to learn to predict the first sentence in a paragraph based on the rest, the model is able to conduct zero-shot inference on unseen tasks such as topic classification and sentiment analysis. Experimental results show that our model outperforms the state-of-the-art baselines on 7 out of 10 tasks. Moreover, the analysis reveals that our model is less sensitive to the prompt design. Our code and pre-trained models are publicly available at \url{https://github.com/DAMO-NLP-SG/SSTuning}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-zero">
<titleInfo>
<title>Zero-Shot Text Classification via Self-Supervised Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaoqun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guizhen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Tuan</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chip</namePart>
<namePart type="given">Hong</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidong</namePart>
<namePart type="family">Bing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing solutions to zero-shot text classification either conduct prompting with pre-trained language models, which is sensitive to the choices of templates, or rely on large-scale annotated data of relevant tasks for meta-tuning. In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning. By exploring the inherent structure of free texts, we propose a new learning objective called first sentence prediction to bridge the gap between unlabeled data and text classification tasks. After tuning the model to learn to predict the first sentence in a paragraph based on the rest, the model is able to conduct zero-shot inference on unseen tasks such as topic classification and sentiment analysis. Experimental results show that our model outperforms the state-of-the-art baselines on 7 out of 10 tasks. Moreover, the analysis reveals that our model is less sensitive to the prompt design. Our code and pre-trained models are publicly available at https://github.com/DAMO-NLP-SG/SSTuning.</abstract>
<identifier type="citekey">liu-etal-2023-zero</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.110</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.110/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1743</start>
<end>1761</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-Shot Text Classification via Self-Supervised Tuning
%A Liu, Chaoqun
%A Zhang, Wenxuan
%A Chen, Guizhen
%A Wu, Xiaobao
%A Luu, Anh Tuan
%A Chang, Chip Hong
%A Bing, Lidong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F liu-etal-2023-zero
%X Existing solutions to zero-shot text classification either conduct prompting with pre-trained language models, which is sensitive to the choices of templates, or rely on large-scale annotated data of relevant tasks for meta-tuning. In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning. By exploring the inherent structure of free texts, we propose a new learning objective called first sentence prediction to bridge the gap between unlabeled data and text classification tasks. After tuning the model to learn to predict the first sentence in a paragraph based on the rest, the model is able to conduct zero-shot inference on unseen tasks such as topic classification and sentiment analysis. Experimental results show that our model outperforms the state-of-the-art baselines on 7 out of 10 tasks. Moreover, the analysis reveals that our model is less sensitive to the prompt design. Our code and pre-trained models are publicly available at https://github.com/DAMO-NLP-SG/SSTuning.
%R 10.18653/v1/2023.findings-acl.110
%U https://aclanthology.org/2023.findings-acl.110/
%U https://doi.org/10.18653/v1/2023.findings-acl.110
%P 1743-1761
Markdown (Informal)
[Zero-Shot Text Classification via Self-Supervised Tuning](https://aclanthology.org/2023.findings-acl.110/) (Liu et al., Findings 2023)
ACL
- Chaoqun Liu, Wenxuan Zhang, Guizhen Chen, Xiaobao Wu, Anh Tuan Luu, Chip Hong Chang, and Lidong Bing. 2023. Zero-Shot Text Classification via Self-Supervised Tuning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1743–1761, Toronto, Canada. Association for Computational Linguistics.