@inproceedings{araujo-de-britto-etal-2021-comparing,
title = "Comparing Supervised Machine Learning Techniques for Genre Analysis in Software Engineering Research Articles",
author = "Ara{\'u}jo de Britto, Felipe and
Castro Ferreira, Thiago and
Nunes, Leonardo Pereira and
Silva Parreiras, Fernando",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.8",
pages = "63--72",
abstract = "Written communication is of utmost importance to the progress of scientific research. The speed of such development, however, may be affected by the scarcity of reviewers to referee the quality of research articles. In this context, automatic approaches that are able to query linguistic segments in written contributions by detecting the presence or absence of common rhetorical patterns have become a necessity. This paper aims to compare supervised machine learning techniques tested to accomplish genre analysis in Introduction sections of software engineering articles. A semi-supervised approach was carried out to augment the number of annotated sentences in SciSents (Avaliable on: ANONYMOUS). Two supervised approaches using SVM and logistic regression were undertaken to assess the F-score for genre analysis in the corpus. A technique based on logistic regression and BERT has been found to perform genre analysis highly satisfactorily with an average of 88.25 on F-score when retrieving patterns at an overall level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="araujo-de-britto-etal-2021-comparing">
<titleInfo>
<title>Comparing Supervised Machine Learning Techniques for Genre Analysis in Software Engineering Research Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Araújo de Britto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiago</namePart>
<namePart type="family">Castro Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="given">Pereira</namePart>
<namePart type="family">Nunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Silva Parreiras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Written communication is of utmost importance to the progress of scientific research. The speed of such development, however, may be affected by the scarcity of reviewers to referee the quality of research articles. In this context, automatic approaches that are able to query linguistic segments in written contributions by detecting the presence or absence of common rhetorical patterns have become a necessity. This paper aims to compare supervised machine learning techniques tested to accomplish genre analysis in Introduction sections of software engineering articles. A semi-supervised approach was carried out to augment the number of annotated sentences in SciSents (Avaliable on: ANONYMOUS). Two supervised approaches using SVM and logistic regression were undertaken to assess the F-score for genre analysis in the corpus. A technique based on logistic regression and BERT has been found to perform genre analysis highly satisfactorily with an average of 88.25 on F-score when retrieving patterns at an overall level.</abstract>
<identifier type="citekey">araujo-de-britto-etal-2021-comparing</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.8</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>63</start>
<end>72</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Supervised Machine Learning Techniques for Genre Analysis in Software Engineering Research Articles
%A Araújo de Britto, Felipe
%A Castro Ferreira, Thiago
%A Nunes, Leonardo Pereira
%A Silva Parreiras, Fernando
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F araujo-de-britto-etal-2021-comparing
%X Written communication is of utmost importance to the progress of scientific research. The speed of such development, however, may be affected by the scarcity of reviewers to referee the quality of research articles. In this context, automatic approaches that are able to query linguistic segments in written contributions by detecting the presence or absence of common rhetorical patterns have become a necessity. This paper aims to compare supervised machine learning techniques tested to accomplish genre analysis in Introduction sections of software engineering articles. A semi-supervised approach was carried out to augment the number of annotated sentences in SciSents (Avaliable on: ANONYMOUS). Two supervised approaches using SVM and logistic regression were undertaken to assess the F-score for genre analysis in the corpus. A technique based on logistic regression and BERT has been found to perform genre analysis highly satisfactorily with an average of 88.25 on F-score when retrieving patterns at an overall level.
%U https://aclanthology.org/2021.ranlp-1.8
%P 63-72
Markdown (Informal)
[Comparing Supervised Machine Learning Techniques for Genre Analysis in Software Engineering Research Articles](https://aclanthology.org/2021.ranlp-1.8) (Araújo de Britto et al., RANLP 2021)
ACL