@inproceedings{zeng-etal-2022-weakly,
title = "Weakly Supervised Text Classification using Supervision Signals from a Language Model",
author = "Zeng, Ziqian and
Ni, Weimin and
Fang, Tianqing and
Li, Xiang and
Zhao, Xinran and
Song, Yangqiu",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.176/",
doi = "10.18653/v1/2022.findings-naacl.176",
pages = "2295--2305",
abstract = "Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document itself and {\textquotedblleft}this article is talking about [MASK].{\textquotedblright} A masked language model can generate words for the [MASK] token. The generated words which summarize the content of a document can be utilized as supervision signals. We propose a latent variable model to learn a word distribution learner which associates generated words to pre-defined categories and a document classifier simultaneously without using any annotated data. Evaluation on three datasets, AGNews, 20Newsgroups, and UCINews, shows that our method can outperform baselines by 2{\%}, 4{\%}, and 3{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2022-weakly">
<titleInfo>
<title>Weakly Supervised Text Classification using Supervision Signals from a Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziqian</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weimin</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianqing</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinran</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangqiu</namePart>
<namePart type="family">Song</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>Findings of the Association for Computational Linguistics: NAACL 2022</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>Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document itself and “this article is talking about [MASK].” A masked language model can generate words for the [MASK] token. The generated words which summarize the content of a document can be utilized as supervision signals. We propose a latent variable model to learn a word distribution learner which associates generated words to pre-defined categories and a document classifier simultaneously without using any annotated data. Evaluation on three datasets, AGNews, 20Newsgroups, and UCINews, shows that our method can outperform baselines by 2%, 4%, and 3%.</abstract>
<identifier type="citekey">zeng-etal-2022-weakly</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.176</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.176/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2295</start>
<end>2305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weakly Supervised Text Classification using Supervision Signals from a Language Model
%A Zeng, Ziqian
%A Ni, Weimin
%A Fang, Tianqing
%A Li, Xiang
%A Zhao, Xinran
%A Song, Yangqiu
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F zeng-etal-2022-weakly
%X Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document itself and “this article is talking about [MASK].” A masked language model can generate words for the [MASK] token. The generated words which summarize the content of a document can be utilized as supervision signals. We propose a latent variable model to learn a word distribution learner which associates generated words to pre-defined categories and a document classifier simultaneously without using any annotated data. Evaluation on three datasets, AGNews, 20Newsgroups, and UCINews, shows that our method can outperform baselines by 2%, 4%, and 3%.
%R 10.18653/v1/2022.findings-naacl.176
%U https://aclanthology.org/2022.findings-naacl.176/
%U https://doi.org/10.18653/v1/2022.findings-naacl.176
%P 2295-2305
Markdown (Informal)
[Weakly Supervised Text Classification using Supervision Signals from a Language Model](https://aclanthology.org/2022.findings-naacl.176/) (Zeng et al., Findings 2022)
ACL