@inproceedings{chen-etal-2020-sibert,
title = "{S}i{B}ert: Enhanced {C}hinese Pre-trained Language Model with Sentence Insertion",
author = "Chen, Jiahao and
Cao, Chenjie and
Jiang, Xiuyan",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.293",
pages = "2405--2412",
abstract = "Pre-trained models have achieved great success in learning unsupervised language representations by self-supervised tasks on large-scale corpora. Recent studies mainly focus on how to fine-tune different downstream tasks from a general pre-trained model. However, some studies show that customized self-supervised tasks for a particular type of downstream task can effectively help the pre-trained model to capture more corresponding knowledge and semantic information. Hence a new pre-training task called Sentence Insertion (SI) is proposed in this paper for Chinese query-passage pairs NLP tasks including answer span prediction, retrieval question answering and sentence level cloze test. The related experiment results indicate that the proposed SI can improve the performance of the Chinese Pre-trained models significantly. Moreover, a word segmentation method called SentencePiece is utilized to further enhance Chinese Bert performance for tasks with long texts. The complete source code is available at \url{https://github.com/ewrfcas/SiBert_tensorflow}.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-sibert">
<titleInfo>
<title>SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiahao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenjie</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuyan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Pre-trained models have achieved great success in learning unsupervised language representations by self-supervised tasks on large-scale corpora. Recent studies mainly focus on how to fine-tune different downstream tasks from a general pre-trained model. However, some studies show that customized self-supervised tasks for a particular type of downstream task can effectively help the pre-trained model to capture more corresponding knowledge and semantic information. Hence a new pre-training task called Sentence Insertion (SI) is proposed in this paper for Chinese query-passage pairs NLP tasks including answer span prediction, retrieval question answering and sentence level cloze test. The related experiment results indicate that the proposed SI can improve the performance of the Chinese Pre-trained models significantly. Moreover, a word segmentation method called SentencePiece is utilized to further enhance Chinese Bert performance for tasks with long texts. The complete source code is available at https://github.com/ewrfcas/SiBert_tensorflow.</abstract>
<identifier type="citekey">chen-etal-2020-sibert</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.293</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2405</start>
<end>2412</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion
%A Chen, Jiahao
%A Cao, Chenjie
%A Jiang, Xiuyan
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F chen-etal-2020-sibert
%X Pre-trained models have achieved great success in learning unsupervised language representations by self-supervised tasks on large-scale corpora. Recent studies mainly focus on how to fine-tune different downstream tasks from a general pre-trained model. However, some studies show that customized self-supervised tasks for a particular type of downstream task can effectively help the pre-trained model to capture more corresponding knowledge and semantic information. Hence a new pre-training task called Sentence Insertion (SI) is proposed in this paper for Chinese query-passage pairs NLP tasks including answer span prediction, retrieval question answering and sentence level cloze test. The related experiment results indicate that the proposed SI can improve the performance of the Chinese Pre-trained models significantly. Moreover, a word segmentation method called SentencePiece is utilized to further enhance Chinese Bert performance for tasks with long texts. The complete source code is available at https://github.com/ewrfcas/SiBert_tensorflow.
%U https://aclanthology.org/2020.lrec-1.293
%P 2405-2412
Markdown (Informal)
[SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion](https://aclanthology.org/2020.lrec-1.293) (Chen et al., LREC 2020)
ACL