@inproceedings{ohashi-etal-2020-text,
title = "Text Classification with Negative Supervision",
author = "Ohashi, Sora and
Takayama, Junya and
Kajiwara, Tomoyuki and
Chu, Chenhui and
Arase, Yuki",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.33",
doi = "10.18653/v1/2020.acl-main.33",
pages = "351--357",
abstract = "Advanced pre-trained models for text representation have achieved state-of-the-art performance on various text classification tasks. However, the discrepancy between the semantic similarity of texts and labelling standards affects classifiers, i.e. leading to lower performance in cases where classifiers should assign different labels to semantically similar texts. To address this problem, we propose a simple multitask learning model that uses negative supervision. Specifically, our model encourages texts with different labels to have distinct representations. Comprehensive experiments show that our model outperforms the state-of-the-art pre-trained model on both single- and multi-label classifications, sentence and document classifications, and classifications in three different languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ohashi-etal-2020-text">
<titleInfo>
<title>Text Classification with Negative Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sora</namePart>
<namePart type="family">Ohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junya</namePart>
<namePart type="family">Takayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Arase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Advanced pre-trained models for text representation have achieved state-of-the-art performance on various text classification tasks. However, the discrepancy between the semantic similarity of texts and labelling standards affects classifiers, i.e. leading to lower performance in cases where classifiers should assign different labels to semantically similar texts. To address this problem, we propose a simple multitask learning model that uses negative supervision. Specifically, our model encourages texts with different labels to have distinct representations. Comprehensive experiments show that our model outperforms the state-of-the-art pre-trained model on both single- and multi-label classifications, sentence and document classifications, and classifications in three different languages.</abstract>
<identifier type="citekey">ohashi-etal-2020-text</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.33</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.33</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>351</start>
<end>357</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Classification with Negative Supervision
%A Ohashi, Sora
%A Takayama, Junya
%A Kajiwara, Tomoyuki
%A Chu, Chenhui
%A Arase, Yuki
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F ohashi-etal-2020-text
%X Advanced pre-trained models for text representation have achieved state-of-the-art performance on various text classification tasks. However, the discrepancy between the semantic similarity of texts and labelling standards affects classifiers, i.e. leading to lower performance in cases where classifiers should assign different labels to semantically similar texts. To address this problem, we propose a simple multitask learning model that uses negative supervision. Specifically, our model encourages texts with different labels to have distinct representations. Comprehensive experiments show that our model outperforms the state-of-the-art pre-trained model on both single- and multi-label classifications, sentence and document classifications, and classifications in three different languages.
%R 10.18653/v1/2020.acl-main.33
%U https://aclanthology.org/2020.acl-main.33
%U https://doi.org/10.18653/v1/2020.acl-main.33
%P 351-357
Markdown (Informal)
[Text Classification with Negative Supervision](https://aclanthology.org/2020.acl-main.33) (Ohashi et al., ACL 2020)
ACL
- Sora Ohashi, Junya Takayama, Tomoyuki Kajiwara, Chenhui Chu, and Yuki Arase. 2020. Text Classification with Negative Supervision. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 351–357, Online. Association for Computational Linguistics.