@inproceedings{iwatsuki-aizawa-2021-communicative,
title = "Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database",
author = "Iwatsuki, Kenichi and
Aizawa, Akiko",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.304",
doi = "10.18653/v1/2021.eacl-main.304",
pages = "3476--3497",
abstract = "Formulaic expressions (FEs), such as {`}in this paper, we propose{'} are frequently used in scientific papers. FEs convey a communicative function (CF), i.e. {`}showing the aim of the paper{'} in the above-mentioned example. Although CF-labelled FEs are helpful in assisting academic writing, the construction of FE databases requires manual labour for assigning CF labels. In this study, we considered a fully automated construction of a CF-labelled FE database using the top{--}down approach, in which the CF labels are first assigned to sentences, and then the FEs are extracted. For the CF-label assignment, we created a CF-labelled sentence dataset, on which we trained a SciBERT classifier. We show that the classifier and dataset can be used to construct FE databases of disciplines that are different from the training data. The accuracy of in-disciplinary classification was more than 80{\%}, while cross-disciplinary classification also worked well. We also propose an FE extraction method, which was applied to the CF-labelled sentences. Finally, we constructed and published a new, large CF-labelled FE database. The evaluation of the final CF-labelled FE database showed that approximately 65{\%} of the FEs are correct and useful, which is sufficiently high considering practical use.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iwatsuki-aizawa-2021-communicative">
<titleInfo>
<title>Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenichi</namePart>
<namePart type="family">Iwatsuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>Formulaic expressions (FEs), such as ‘in this paper, we propose’ are frequently used in scientific papers. FEs convey a communicative function (CF), i.e. ‘showing the aim of the paper’ in the above-mentioned example. Although CF-labelled FEs are helpful in assisting academic writing, the construction of FE databases requires manual labour for assigning CF labels. In this study, we considered a fully automated construction of a CF-labelled FE database using the top–down approach, in which the CF labels are first assigned to sentences, and then the FEs are extracted. For the CF-label assignment, we created a CF-labelled sentence dataset, on which we trained a SciBERT classifier. We show that the classifier and dataset can be used to construct FE databases of disciplines that are different from the training data. The accuracy of in-disciplinary classification was more than 80%, while cross-disciplinary classification also worked well. We also propose an FE extraction method, which was applied to the CF-labelled sentences. Finally, we constructed and published a new, large CF-labelled FE database. The evaluation of the final CF-labelled FE database showed that approximately 65% of the FEs are correct and useful, which is sufficiently high considering practical use.</abstract>
<identifier type="citekey">iwatsuki-aizawa-2021-communicative</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.304</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.304</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>3476</start>
<end>3497</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database
%A Iwatsuki, Kenichi
%A Aizawa, Akiko
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F iwatsuki-aizawa-2021-communicative
%X Formulaic expressions (FEs), such as ‘in this paper, we propose’ are frequently used in scientific papers. FEs convey a communicative function (CF), i.e. ‘showing the aim of the paper’ in the above-mentioned example. Although CF-labelled FEs are helpful in assisting academic writing, the construction of FE databases requires manual labour for assigning CF labels. In this study, we considered a fully automated construction of a CF-labelled FE database using the top–down approach, in which the CF labels are first assigned to sentences, and then the FEs are extracted. For the CF-label assignment, we created a CF-labelled sentence dataset, on which we trained a SciBERT classifier. We show that the classifier and dataset can be used to construct FE databases of disciplines that are different from the training data. The accuracy of in-disciplinary classification was more than 80%, while cross-disciplinary classification also worked well. We also propose an FE extraction method, which was applied to the CF-labelled sentences. Finally, we constructed and published a new, large CF-labelled FE database. The evaluation of the final CF-labelled FE database showed that approximately 65% of the FEs are correct and useful, which is sufficiently high considering practical use.
%R 10.18653/v1/2021.eacl-main.304
%U https://aclanthology.org/2021.eacl-main.304
%U https://doi.org/10.18653/v1/2021.eacl-main.304
%P 3476-3497
Markdown (Informal)
[Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database](https://aclanthology.org/2021.eacl-main.304) (Iwatsuki & Aizawa, EACL 2021)
ACL