@inproceedings{escoter-etal-2017-grouping,
title = "Grouping business news stories based on salience of named entities",
author = "Escoter, Lloren{\c{c}} and
Pivovarova, Lidia and
Du, Mian and
Katinskaia, Anisia and
Yangarber, Roman",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-1103",
pages = "1096--1106",
abstract = "In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles. Depending on the relative importance of the story, the number of versions can reach dozens or hundreds within a day. The text in these versions may be nearly identical or quite different. Linking multiple versions of a story into a single group brings several important benefits to the end-user{--}reducing the cognitive load on the reader, as well as signaling the relative importance of the story. We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience{--}a measure of importance of named entities in the text. We demonstrate that features beyond keywords yield substantial improvements, verified on a manually-annotated corpus of business news stories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="escoter-etal-2017-grouping">
<titleInfo>
<title>Grouping business news stories based on salience of named entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Llorenç</namePart>
<namePart type="family">Escoter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mian</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anisia</namePart>
<namePart type="family">Katinskaia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles. Depending on the relative importance of the story, the number of versions can reach dozens or hundreds within a day. The text in these versions may be nearly identical or quite different. Linking multiple versions of a story into a single group brings several important benefits to the end-user–reducing the cognitive load on the reader, as well as signaling the relative importance of the story. We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience–a measure of importance of named entities in the text. We demonstrate that features beyond keywords yield substantial improvements, verified on a manually-annotated corpus of business news stories.</abstract>
<identifier type="citekey">escoter-etal-2017-grouping</identifier>
<location>
<url>https://aclanthology.org/E17-1103</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>1096</start>
<end>1106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grouping business news stories based on salience of named entities
%A Escoter, Llorenç
%A Pivovarova, Lidia
%A Du, Mian
%A Katinskaia, Anisia
%A Yangarber, Roman
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F escoter-etal-2017-grouping
%X In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles. Depending on the relative importance of the story, the number of versions can reach dozens or hundreds within a day. The text in these versions may be nearly identical or quite different. Linking multiple versions of a story into a single group brings several important benefits to the end-user–reducing the cognitive load on the reader, as well as signaling the relative importance of the story. We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience–a measure of importance of named entities in the text. We demonstrate that features beyond keywords yield substantial improvements, verified on a manually-annotated corpus of business news stories.
%U https://aclanthology.org/E17-1103
%P 1096-1106
Markdown (Informal)
[Grouping business news stories based on salience of named entities](https://aclanthology.org/E17-1103) (Escoter et al., EACL 2017)
ACL
- Llorenç Escoter, Lidia Pivovarova, Mian Du, Anisia Katinskaia, and Roman Yangarber. 2017. Grouping business news stories based on salience of named entities. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 1096–1106, Valencia, Spain. Association for Computational Linguistics.