@inproceedings{shimizu-etal-2018-pretraining,
title = "Pretraining Sentiment Classifiers with Unlabeled Dialog Data",
author = "Shimizu, Toru and
Shimizu, Nobuyuki and
Kobayashi, Hayato",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-2121",
doi = "10.18653/v1/P18-2121",
pages = "764--770",
abstract = "The huge cost of creating labeled training data is a common problem for supervised learning tasks such as sentiment classification. Recent studies showed that pretraining with unlabeled data via a language model can improve the performance of classification models. In this paper, we take the concept a step further by using a conditional language model, instead of a language model. Specifically, we address a sentiment classification task for a tweet analysis service as a case study and propose a pretraining strategy with unlabeled dialog data (tweet-reply pairs) via an encoder-decoder model. Experimental results show that our strategy can improve the performance of sentiment classifiers and outperform several state-of-the-art strategies including language model pretraining.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shimizu-etal-2018-pretraining">
<titleInfo>
<title>Pretraining Sentiment Classifiers with Unlabeled Dialog Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toru</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nobuyuki</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayato</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The huge cost of creating labeled training data is a common problem for supervised learning tasks such as sentiment classification. Recent studies showed that pretraining with unlabeled data via a language model can improve the performance of classification models. In this paper, we take the concept a step further by using a conditional language model, instead of a language model. Specifically, we address a sentiment classification task for a tweet analysis service as a case study and propose a pretraining strategy with unlabeled dialog data (tweet-reply pairs) via an encoder-decoder model. Experimental results show that our strategy can improve the performance of sentiment classifiers and outperform several state-of-the-art strategies including language model pretraining.</abstract>
<identifier type="citekey">shimizu-etal-2018-pretraining</identifier>
<identifier type="doi">10.18653/v1/P18-2121</identifier>
<location>
<url>https://aclanthology.org/P18-2121</url>
</location>
<part>
<date>2018-jul</date>
<extent unit="page">
<start>764</start>
<end>770</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pretraining Sentiment Classifiers with Unlabeled Dialog Data
%A Shimizu, Toru
%A Shimizu, Nobuyuki
%A Kobayashi, Hayato
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 jul
%I Association for Computational Linguistics
%C Melbourne, Australia
%F shimizu-etal-2018-pretraining
%X The huge cost of creating labeled training data is a common problem for supervised learning tasks such as sentiment classification. Recent studies showed that pretraining with unlabeled data via a language model can improve the performance of classification models. In this paper, we take the concept a step further by using a conditional language model, instead of a language model. Specifically, we address a sentiment classification task for a tweet analysis service as a case study and propose a pretraining strategy with unlabeled dialog data (tweet-reply pairs) via an encoder-decoder model. Experimental results show that our strategy can improve the performance of sentiment classifiers and outperform several state-of-the-art strategies including language model pretraining.
%R 10.18653/v1/P18-2121
%U https://aclanthology.org/P18-2121
%U https://doi.org/10.18653/v1/P18-2121
%P 764-770
Markdown (Informal)
[Pretraining Sentiment Classifiers with Unlabeled Dialog Data](https://aclanthology.org/P18-2121) (Shimizu et al., ACL 2018)
ACL
- Toru Shimizu, Nobuyuki Shimizu, and Hayato Kobayashi. 2018. Pretraining Sentiment Classifiers with Unlabeled Dialog Data. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 764–770, Melbourne, Australia. Association for Computational Linguistics.