@inproceedings{zhang-etal-2022-complicate,
title = "Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification",
author = "Zhang, Xu and
Liu, Zejie and
Xiang, Yanzheng and
Zhou, Deyu",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.97",
pages = "1136--1145",
abstract = "With the development of pre-trained models (PTMs), the performance of text classification has been continuously improved by directly employing the features generated by PTMs. However such way might not fully explore the knowledge in PTMs as it is constrained by the difficulty of the task. Compared to difficult task, the learning algorithms tend to saturate early on the simple task. Moreover, the native sentence representations derived from BERT are prone to be collapsed and directly employing such representation for text classification might fail to fully capture discriminative features. In order to address these issues, in this paper we propose a novel framework for text classification which implements a two-stage training strategy. In the pre-training stage, auxiliary labels are introduced to increase the task difficulties and to fully exploit the knowledge in the pre-trained model. In the fine-tuning stage, the textual representation learned in the pre-training stage is employed and the classifier is fine-tuned to obtain better classification performance. Experiments were conducted on six text classification corpora and the results showed that the proposed framework outperformed several state-of-the-art baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-complicate">
<titleInfo>
<title>Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zejie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanzheng</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the development of pre-trained models (PTMs), the performance of text classification has been continuously improved by directly employing the features generated by PTMs. However such way might not fully explore the knowledge in PTMs as it is constrained by the difficulty of the task. Compared to difficult task, the learning algorithms tend to saturate early on the simple task. Moreover, the native sentence representations derived from BERT are prone to be collapsed and directly employing such representation for text classification might fail to fully capture discriminative features. In order to address these issues, in this paper we propose a novel framework for text classification which implements a two-stage training strategy. In the pre-training stage, auxiliary labels are introduced to increase the task difficulties and to fully exploit the knowledge in the pre-trained model. In the fine-tuning stage, the textual representation learned in the pre-training stage is employed and the classifier is fine-tuned to obtain better classification performance. Experiments were conducted on six text classification corpora and the results showed that the proposed framework outperformed several state-of-the-art baselines.</abstract>
<identifier type="citekey">zhang-etal-2022-complicate</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.97</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>1136</start>
<end>1145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification
%A Zhang, Xu
%A Liu, Zejie
%A Xiang, Yanzheng
%A Zhou, Deyu
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F zhang-etal-2022-complicate
%X With the development of pre-trained models (PTMs), the performance of text classification has been continuously improved by directly employing the features generated by PTMs. However such way might not fully explore the knowledge in PTMs as it is constrained by the difficulty of the task. Compared to difficult task, the learning algorithms tend to saturate early on the simple task. Moreover, the native sentence representations derived from BERT are prone to be collapsed and directly employing such representation for text classification might fail to fully capture discriminative features. In order to address these issues, in this paper we propose a novel framework for text classification which implements a two-stage training strategy. In the pre-training stage, auxiliary labels are introduced to increase the task difficulties and to fully exploit the knowledge in the pre-trained model. In the fine-tuning stage, the textual representation learned in the pre-training stage is employed and the classifier is fine-tuned to obtain better classification performance. Experiments were conducted on six text classification corpora and the results showed that the proposed framework outperformed several state-of-the-art baselines.
%U https://aclanthology.org/2022.coling-1.97
%P 1136-1145
Markdown (Informal)
[Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification](https://aclanthology.org/2022.coling-1.97) (Zhang et al., COLING 2022)
ACL