@inproceedings{born-etal-2020-dataset,
title = "Dataset Reproducibility and {IR} Methods in Timeline Summarization",
author = "Born, Leo and
Bacher, Maximilian and
Markert, Katja",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.218",
pages = "1763--1771",
abstract = "Timeline summarization (TLS) generates a dated overview of real-world events based on event-specific corpora. The two standard datasets for this task were collected using Google searches for news reports on given events. Not only is this IR method not reproducible at different search times, it also uses components (such as document popularity) that are not always available for any large news corpus. It is unclear how TLS algorithms fare when provided with event corpora collected with varying IR methods. We therefore construct event-specific corpora from a large static background corpus, the newsroom dataset, using differing, relatively simple IR methods based on raw text alone. We show that the choice of IR method plays a crucial role in the performance of various TLS algorithms. A weak TLS algorithm can even match a stronger one by employing a stronger IR method in the data collection phase. Furthermore, the results of TLS systems are often highly sensitive to additional sentence filtering. We consequently advocate for integrating IR into the development of TLS systems and having a common static background corpus for evaluation of TLS systems.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="born-etal-2020-dataset">
<titleInfo>
<title>Dataset Reproducibility and IR Methods in Timeline Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Born</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Bacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katja</namePart>
<namePart type="family">Markert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Timeline summarization (TLS) generates a dated overview of real-world events based on event-specific corpora. The two standard datasets for this task were collected using Google searches for news reports on given events. Not only is this IR method not reproducible at different search times, it also uses components (such as document popularity) that are not always available for any large news corpus. It is unclear how TLS algorithms fare when provided with event corpora collected with varying IR methods. We therefore construct event-specific corpora from a large static background corpus, the newsroom dataset, using differing, relatively simple IR methods based on raw text alone. We show that the choice of IR method plays a crucial role in the performance of various TLS algorithms. A weak TLS algorithm can even match a stronger one by employing a stronger IR method in the data collection phase. Furthermore, the results of TLS systems are often highly sensitive to additional sentence filtering. We consequently advocate for integrating IR into the development of TLS systems and having a common static background corpus for evaluation of TLS systems.</abstract>
<identifier type="citekey">born-etal-2020-dataset</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.218</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1763</start>
<end>1771</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dataset Reproducibility and IR Methods in Timeline Summarization
%A Born, Leo
%A Bacher, Maximilian
%A Markert, Katja
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F born-etal-2020-dataset
%X Timeline summarization (TLS) generates a dated overview of real-world events based on event-specific corpora. The two standard datasets for this task were collected using Google searches for news reports on given events. Not only is this IR method not reproducible at different search times, it also uses components (such as document popularity) that are not always available for any large news corpus. It is unclear how TLS algorithms fare when provided with event corpora collected with varying IR methods. We therefore construct event-specific corpora from a large static background corpus, the newsroom dataset, using differing, relatively simple IR methods based on raw text alone. We show that the choice of IR method plays a crucial role in the performance of various TLS algorithms. A weak TLS algorithm can even match a stronger one by employing a stronger IR method in the data collection phase. Furthermore, the results of TLS systems are often highly sensitive to additional sentence filtering. We consequently advocate for integrating IR into the development of TLS systems and having a common static background corpus for evaluation of TLS systems.
%U https://aclanthology.org/2020.lrec-1.218
%P 1763-1771
Markdown (Informal)
[Dataset Reproducibility and IR Methods in Timeline Summarization](https://aclanthology.org/2020.lrec-1.218) (Born et al., LREC 2020)
ACL