@inproceedings{zagar-robnik-sikonja-2021-unsupervised,
title = "Unsupervised Approach to Multilingual User Comments Summarization",
author = "{\v{Z}}agar, Ale{\v{s}} and
Robnik-{\v{S}}ikonja, Marko",
editor = "Toivonen, Hannu and
Boggia, Michele",
booktitle = "Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.hackashop-1.13",
pages = "89--98",
abstract = "User commenting is a valuable feature of many news outlets, enabling them a contact with readers and enabling readers to express their opinion, provide different viewpoints, and even complementary information. Yet, large volumes of user comments are hard to filter, let alone read and extract relevant information. The research on the summarization of user comments is still in its infancy, and human-created summarization datasets are scarce, especially for less-resourced languages. To address this issue, we propose an unsupervised approach to user comments summarization, which uses a modern multilingual representation of sentences together with standard extractive summarization techniques. Our comparison of different sentence representation approaches coupled with different summarization approaches shows that the most successful combinations are the same in news and comment summarization. The empirical results and presented visualisation show usefulness of the proposed methodology for several languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zagar-robnik-sikonja-2021-unsupervised">
<titleInfo>
<title>Unsupervised Approach to Multilingual User Comments Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleš</namePart>
<namePart type="family">Žagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Robnik-Šikonja</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 EACL Hackashop on News Media Content Analysis and Automated Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannu</namePart>
<namePart type="family">Toivonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Boggia</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>User commenting is a valuable feature of many news outlets, enabling them a contact with readers and enabling readers to express their opinion, provide different viewpoints, and even complementary information. Yet, large volumes of user comments are hard to filter, let alone read and extract relevant information. The research on the summarization of user comments is still in its infancy, and human-created summarization datasets are scarce, especially for less-resourced languages. To address this issue, we propose an unsupervised approach to user comments summarization, which uses a modern multilingual representation of sentences together with standard extractive summarization techniques. Our comparison of different sentence representation approaches coupled with different summarization approaches shows that the most successful combinations are the same in news and comment summarization. The empirical results and presented visualisation show usefulness of the proposed methodology for several languages.</abstract>
<identifier type="citekey">zagar-robnik-sikonja-2021-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2021.hackashop-1.13</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>89</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Approach to Multilingual User Comments Summarization
%A Žagar, Aleš
%A Robnik-Šikonja, Marko
%Y Toivonen, Hannu
%Y Boggia, Michele
%S Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F zagar-robnik-sikonja-2021-unsupervised
%X User commenting is a valuable feature of many news outlets, enabling them a contact with readers and enabling readers to express their opinion, provide different viewpoints, and even complementary information. Yet, large volumes of user comments are hard to filter, let alone read and extract relevant information. The research on the summarization of user comments is still in its infancy, and human-created summarization datasets are scarce, especially for less-resourced languages. To address this issue, we propose an unsupervised approach to user comments summarization, which uses a modern multilingual representation of sentences together with standard extractive summarization techniques. Our comparison of different sentence representation approaches coupled with different summarization approaches shows that the most successful combinations are the same in news and comment summarization. The empirical results and presented visualisation show usefulness of the proposed methodology for several languages.
%U https://aclanthology.org/2021.hackashop-1.13
%P 89-98
Markdown (Informal)
[Unsupervised Approach to Multilingual User Comments Summarization](https://aclanthology.org/2021.hackashop-1.13) (Žagar & Robnik-Šikonja, Hackashop 2021)
ACL