@inproceedings{kishimoto-etal-2020-adapting,
title = "Adapting {BERT} to Implicit Discourse Relation Classification with a Focus on Discourse Connectives",
author = "Kishimoto, Yudai and
Murawaki, Yugo and
Kurohashi, Sadao",
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-1.145/",
pages = "1152--1158",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "BERT, a neural network-based language model pre-trained on large corpora, is a breakthrough in natural language processing, significantly outperforming previous state-of-the-art models in numerous tasks. However, there have been few reports on its application to implicit discourse relation classification, and it is not clear how BERT is best adapted to the task. In this paper, we test three methods of adaptation. (1) We perform additional pre-training on text tailored to discourse classification. (2) In expectation of knowledge transfer from explicit discourse relations to implicit discourse relations, we add a task named explicit connective prediction at the additional pre-training step. (3) To exploit implicit connectives given by treebank annotators, we add a task named implicit connective prediction at the fine-tuning step. We demonstrate that these three techniques can be combined straightforwardly in a single training pipeline. Through comprehensive experiments, we found that the first and second techniques provide additional gain while the last one did not."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kishimoto-etal-2020-adapting">
<titleInfo>
<title>Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yudai</namePart>
<namePart type="family">Kishimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yugo</namePart>
<namePart type="family">Murawaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">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>BERT, a neural network-based language model pre-trained on large corpora, is a breakthrough in natural language processing, significantly outperforming previous state-of-the-art models in numerous tasks. However, there have been few reports on its application to implicit discourse relation classification, and it is not clear how BERT is best adapted to the task. In this paper, we test three methods of adaptation. (1) We perform additional pre-training on text tailored to discourse classification. (2) In expectation of knowledge transfer from explicit discourse relations to implicit discourse relations, we add a task named explicit connective prediction at the additional pre-training step. (3) To exploit implicit connectives given by treebank annotators, we add a task named implicit connective prediction at the fine-tuning step. We demonstrate that these three techniques can be combined straightforwardly in a single training pipeline. Through comprehensive experiments, we found that the first and second techniques provide additional gain while the last one did not.</abstract>
<identifier type="citekey">kishimoto-etal-2020-adapting</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.145/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1152</start>
<end>1158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives
%A Kishimoto, Yudai
%A Murawaki, Yugo
%A Kurohashi, Sadao
%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 eng
%F kishimoto-etal-2020-adapting
%X BERT, a neural network-based language model pre-trained on large corpora, is a breakthrough in natural language processing, significantly outperforming previous state-of-the-art models in numerous tasks. However, there have been few reports on its application to implicit discourse relation classification, and it is not clear how BERT is best adapted to the task. In this paper, we test three methods of adaptation. (1) We perform additional pre-training on text tailored to discourse classification. (2) In expectation of knowledge transfer from explicit discourse relations to implicit discourse relations, we add a task named explicit connective prediction at the additional pre-training step. (3) To exploit implicit connectives given by treebank annotators, we add a task named implicit connective prediction at the fine-tuning step. We demonstrate that these three techniques can be combined straightforwardly in a single training pipeline. Through comprehensive experiments, we found that the first and second techniques provide additional gain while the last one did not.
%U https://aclanthology.org/2020.lrec-1.145/
%P 1152-1158
Markdown (Informal)
[Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives](https://aclanthology.org/2020.lrec-1.145/) (Kishimoto et al., LREC 2020)
ACL