@inproceedings{kim-etal-2020-multi-pretraining,
title = "Multi-pretraining for Large-scale Text Classification",
author = "Kim, Kang-Min and
Hyeon, Bumsu and
Kim, Yeachan and
Park, Jun-Hyung and
Lee, SangKeun",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.185",
doi = "10.18653/v1/2020.findings-emnlp.185",
pages = "2041--2050",
abstract = "Deep neural network-based pretraining methods have achieved impressive results in many natural language processing tasks including text classification. However, their applicability to large-scale text classification with numerous categories (e.g., several thousands) is yet to be well-studied, where the training data is insufficient and skewed in terms of categories. In addition, existing pretraining methods usually involve excessive computation and memory overheads. In this paper, we develop a novel multi-pretraining framework for large-scale text classification. This multi-pretraining framework includes both a self-supervised pretraining and a weakly supervised pretraining. We newly introduce an out-of-context words detection task on the unlabeled data as the self-supervised pretraining. It captures the topic-consistency of words used in sentences, which is proven to be useful for text classification. In addition, we propose a weakly supervised pretraining, where labels for text classification are obtained automatically from an existing approach. Experimental results clearly show that both pretraining approaches are effective for large-scale text classification task. The proposed scheme exhibits significant improvements as much as 3.8{\%} in terms of macro-averaging F1-score over strong pretraining methods, while being computationally efficient.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2020-multi-pretraining">
<titleInfo>
<title>Multi-pretraining for Large-scale Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kang-Min</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bumsu</namePart>
<namePart type="family">Hyeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeachan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun-Hyung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SangKeun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Deep neural network-based pretraining methods have achieved impressive results in many natural language processing tasks including text classification. However, their applicability to large-scale text classification with numerous categories (e.g., several thousands) is yet to be well-studied, where the training data is insufficient and skewed in terms of categories. In addition, existing pretraining methods usually involve excessive computation and memory overheads. In this paper, we develop a novel multi-pretraining framework for large-scale text classification. This multi-pretraining framework includes both a self-supervised pretraining and a weakly supervised pretraining. We newly introduce an out-of-context words detection task on the unlabeled data as the self-supervised pretraining. It captures the topic-consistency of words used in sentences, which is proven to be useful for text classification. In addition, we propose a weakly supervised pretraining, where labels for text classification are obtained automatically from an existing approach. Experimental results clearly show that both pretraining approaches are effective for large-scale text classification task. The proposed scheme exhibits significant improvements as much as 3.8% in terms of macro-averaging F1-score over strong pretraining methods, while being computationally efficient.</abstract>
<identifier type="citekey">kim-etal-2020-multi-pretraining</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.185</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.185</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2041</start>
<end>2050</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-pretraining for Large-scale Text Classification
%A Kim, Kang-Min
%A Hyeon, Bumsu
%A Kim, Yeachan
%A Park, Jun-Hyung
%A Lee, SangKeun
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kim-etal-2020-multi-pretraining
%X Deep neural network-based pretraining methods have achieved impressive results in many natural language processing tasks including text classification. However, their applicability to large-scale text classification with numerous categories (e.g., several thousands) is yet to be well-studied, where the training data is insufficient and skewed in terms of categories. In addition, existing pretraining methods usually involve excessive computation and memory overheads. In this paper, we develop a novel multi-pretraining framework for large-scale text classification. This multi-pretraining framework includes both a self-supervised pretraining and a weakly supervised pretraining. We newly introduce an out-of-context words detection task on the unlabeled data as the self-supervised pretraining. It captures the topic-consistency of words used in sentences, which is proven to be useful for text classification. In addition, we propose a weakly supervised pretraining, where labels for text classification are obtained automatically from an existing approach. Experimental results clearly show that both pretraining approaches are effective for large-scale text classification task. The proposed scheme exhibits significant improvements as much as 3.8% in terms of macro-averaging F1-score over strong pretraining methods, while being computationally efficient.
%R 10.18653/v1/2020.findings-emnlp.185
%U https://aclanthology.org/2020.findings-emnlp.185
%U https://doi.org/10.18653/v1/2020.findings-emnlp.185
%P 2041-2050
Markdown (Informal)
[Multi-pretraining for Large-scale Text Classification](https://aclanthology.org/2020.findings-emnlp.185) (Kim et al., Findings 2020)
ACL
- Kang-Min Kim, Bumsu Hyeon, Yeachan Kim, Jun-Hyung Park, and SangKeun Lee. 2020. Multi-pretraining for Large-scale Text Classification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2041–2050, Online. Association for Computational Linguistics.