@inproceedings{patro-baruah-2021-simple,
title = "A Simple Three-Step Approach for the Automatic Detection of Exaggerated Statements in Health Science News",
author = "Patro, Jasabanta and
Baruah, Sabyasachee",
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.289",
doi = "10.18653/v1/2021.eacl-main.289",
pages = "3293--3305",
abstract = "There is a huge difference between a scientific journal reporting {`}wine consumption might be correlated to cancer{'}, and a media outlet publishing {`}wine causes cancer{'} citing the journal{'}s results. The above example is a typical case of a scientific statement being exaggerated as an outcome of the rising problem of media manipulation. Given a pair of statements (say one from the source journal article and the other from the news article covering the results published in the journal), is it possible to ascertain with some confidence whether one is an exaggerated version of the other? This paper presents a surprisingly simple yet rational three-step approach that performs best for this task. We solve the task by breaking it into three sub-tasks as follows {--} (a) given a statement from a scientific paper or press release, we first extract relation phrases (e.g., {`}causes{'} versus {`}might be correlated to{'}) connecting the dependent (e.g., {`}cancer{'}) and the independent ({`}wine{'}) variable, (b) classify the strength of the relationship phrase extracted and (c) compare the strengths of the relation phrases extracted from the statements to identify whether one statement contains an exaggerated version of the other, and to what extent. Through rigorous experiments, we demonstrate that our simple approach by far outperforms baseline models that compare state-of-the-art embedding of the statement pairs through a binary classifier or recast the problem as a textual entailment task, which appears to be a very natural choice in this settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="patro-baruah-2021-simple">
<titleInfo>
<title>A Simple Three-Step Approach for the Automatic Detection of Exaggerated Statements in Health Science News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasabanta</namePart>
<namePart type="family">Patro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabyasachee</namePart>
<namePart type="family">Baruah</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>There is a huge difference between a scientific journal reporting ‘wine consumption might be correlated to cancer’, and a media outlet publishing ‘wine causes cancer’ citing the journal’s results. The above example is a typical case of a scientific statement being exaggerated as an outcome of the rising problem of media manipulation. Given a pair of statements (say one from the source journal article and the other from the news article covering the results published in the journal), is it possible to ascertain with some confidence whether one is an exaggerated version of the other? This paper presents a surprisingly simple yet rational three-step approach that performs best for this task. We solve the task by breaking it into three sub-tasks as follows – (a) given a statement from a scientific paper or press release, we first extract relation phrases (e.g., ‘causes’ versus ‘might be correlated to’) connecting the dependent (e.g., ‘cancer’) and the independent (‘wine’) variable, (b) classify the strength of the relationship phrase extracted and (c) compare the strengths of the relation phrases extracted from the statements to identify whether one statement contains an exaggerated version of the other, and to what extent. Through rigorous experiments, we demonstrate that our simple approach by far outperforms baseline models that compare state-of-the-art embedding of the statement pairs through a binary classifier or recast the problem as a textual entailment task, which appears to be a very natural choice in this settings.</abstract>
<identifier type="citekey">patro-baruah-2021-simple</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.289</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.289</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>3293</start>
<end>3305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simple Three-Step Approach for the Automatic Detection of Exaggerated Statements in Health Science News
%A Patro, Jasabanta
%A Baruah, Sabyasachee
%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 patro-baruah-2021-simple
%X There is a huge difference between a scientific journal reporting ‘wine consumption might be correlated to cancer’, and a media outlet publishing ‘wine causes cancer’ citing the journal’s results. The above example is a typical case of a scientific statement being exaggerated as an outcome of the rising problem of media manipulation. Given a pair of statements (say one from the source journal article and the other from the news article covering the results published in the journal), is it possible to ascertain with some confidence whether one is an exaggerated version of the other? This paper presents a surprisingly simple yet rational three-step approach that performs best for this task. We solve the task by breaking it into three sub-tasks as follows – (a) given a statement from a scientific paper or press release, we first extract relation phrases (e.g., ‘causes’ versus ‘might be correlated to’) connecting the dependent (e.g., ‘cancer’) and the independent (‘wine’) variable, (b) classify the strength of the relationship phrase extracted and (c) compare the strengths of the relation phrases extracted from the statements to identify whether one statement contains an exaggerated version of the other, and to what extent. Through rigorous experiments, we demonstrate that our simple approach by far outperforms baseline models that compare state-of-the-art embedding of the statement pairs through a binary classifier or recast the problem as a textual entailment task, which appears to be a very natural choice in this settings.
%R 10.18653/v1/2021.eacl-main.289
%U https://aclanthology.org/2021.eacl-main.289
%U https://doi.org/10.18653/v1/2021.eacl-main.289
%P 3293-3305
Markdown (Informal)
[A Simple Three-Step Approach for the Automatic Detection of Exaggerated Statements in Health Science News](https://aclanthology.org/2021.eacl-main.289) (Patro & Baruah, EACL 2021)
ACL