@inproceedings{urlana-etal-2022-tesum,
title = "{T}e{S}um: Human-Generated Abstractive Summarization Corpus for {T}elugu",
author = "Urlana, Ashok and
Surange, Nirmal and
Baswani, Pavan and
Ravva, Priyanka and
Shrivastava, Manish",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.614",
pages = "5712--5722",
abstract = "Expert human annotation for summarization is definitely an expensive task, and can not be done on huge scales. But with this work, we show that even with a crowd sourced summary generation approach, quality can be controlled by aggressive expert informed filtering and sampling-based human evaluation. We propose a pipeline that crowd-sources summarization data and then aggressively filters the content via: automatic and partial expert evaluation. Using this pipeline we create a high-quality Telugu Abstractive Summarization dataset (TeSum) which we validate with sampling-based human evaluation. We also provide baseline numbers for various models commonly used for summarization. A number of recently released datasets for summarization, scraped the web-content relying on the assumption that summary is made available with the article by the publishers. While this assumption holds for multiple resources (or news-sites) in English, it should not be generalised across languages without thorough analysis and verification. Our analysis clearly shows that this assumption does not hold true for most Indian language news resources. We show that our proposed filtration pipeline can even be applied to these large-scale scraped datasets to extract better quality article-summary pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="urlana-etal-2022-tesum">
<titleInfo>
<title>TeSum: Human-Generated Abstractive Summarization Corpus for Telugu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashok</namePart>
<namePart type="family">Urlana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nirmal</namePart>
<namePart type="family">Surange</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavan</namePart>
<namePart type="family">Baswani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Ravva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>Expert human annotation for summarization is definitely an expensive task, and can not be done on huge scales. But with this work, we show that even with a crowd sourced summary generation approach, quality can be controlled by aggressive expert informed filtering and sampling-based human evaluation. We propose a pipeline that crowd-sources summarization data and then aggressively filters the content via: automatic and partial expert evaluation. Using this pipeline we create a high-quality Telugu Abstractive Summarization dataset (TeSum) which we validate with sampling-based human evaluation. We also provide baseline numbers for various models commonly used for summarization. A number of recently released datasets for summarization, scraped the web-content relying on the assumption that summary is made available with the article by the publishers. While this assumption holds for multiple resources (or news-sites) in English, it should not be generalised across languages without thorough analysis and verification. Our analysis clearly shows that this assumption does not hold true for most Indian language news resources. We show that our proposed filtration pipeline can even be applied to these large-scale scraped datasets to extract better quality article-summary pairs.</abstract>
<identifier type="citekey">urlana-etal-2022-tesum</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.614</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5712</start>
<end>5722</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeSum: Human-Generated Abstractive Summarization Corpus for Telugu
%A Urlana, Ashok
%A Surange, Nirmal
%A Baswani, Pavan
%A Ravva, Priyanka
%A Shrivastava, Manish
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F urlana-etal-2022-tesum
%X Expert human annotation for summarization is definitely an expensive task, and can not be done on huge scales. But with this work, we show that even with a crowd sourced summary generation approach, quality can be controlled by aggressive expert informed filtering and sampling-based human evaluation. We propose a pipeline that crowd-sources summarization data and then aggressively filters the content via: automatic and partial expert evaluation. Using this pipeline we create a high-quality Telugu Abstractive Summarization dataset (TeSum) which we validate with sampling-based human evaluation. We also provide baseline numbers for various models commonly used for summarization. A number of recently released datasets for summarization, scraped the web-content relying on the assumption that summary is made available with the article by the publishers. While this assumption holds for multiple resources (or news-sites) in English, it should not be generalised across languages without thorough analysis and verification. Our analysis clearly shows that this assumption does not hold true for most Indian language news resources. We show that our proposed filtration pipeline can even be applied to these large-scale scraped datasets to extract better quality article-summary pairs.
%U https://aclanthology.org/2022.lrec-1.614
%P 5712-5722
Markdown (Informal)
[TeSum: Human-Generated Abstractive Summarization Corpus for Telugu](https://aclanthology.org/2022.lrec-1.614) (Urlana et al., LREC 2022)
ACL