@inproceedings{mckelvey-etal-2017-aligning,
title = "Aligning Entity Names with Online Aliases on {T}witter",
author = "McKelvey, Kevin and
Goutzounis, Peter and
da Cruz, Stephen and
Chambers, Nathanael",
editor = "Ku, Lun-Wei and
Li, Cheng-Te",
booktitle = "Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1104",
doi = "10.18653/v1/W17-1104",
pages = "25--35",
abstract = "This paper presents new models that automatically align online aliases with their real entity names. Many research applications rely on identifying entity names in text, but people often refer to entities with unexpected nicknames and aliases. For example, The King and King James are aliases for Lebron James, a professional basketball player. Recent work on entity linking attempts to resolve mentions to knowledge base entries, like a wikipedia page, but linking is unfortunately limited to well-known entities with pre-built pages. This paper asks a more basic question: can aliases be aligned without background knowledge of the entity? Further, can the semantics surrounding alias mentions be used to inform alignments? We describe statistical models that make decisions based on the lexicographic properties of the aliases with their semantic context in a large corpus of tweets. We experiment on a database of Twitter users and their usernames, and present the first human evaluation for this task. Alignment accuracy approaches human performance at 81{\%}, and we show that while lexicographic features are most important, the semantic context of an alias further improves classification accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mckelvey-etal-2017-aligning">
<titleInfo>
<title>Aligning Entity Names with Online Aliases on Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">McKelvey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Goutzounis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">da Cruz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathanael</namePart>
<namePart type="family">Chambers</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 Fifth International Workshop on Natural Language Processing for Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng-Te</namePart>
<namePart type="family">Li</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>This paper presents new models that automatically align online aliases with their real entity names. Many research applications rely on identifying entity names in text, but people often refer to entities with unexpected nicknames and aliases. For example, The King and King James are aliases for Lebron James, a professional basketball player. Recent work on entity linking attempts to resolve mentions to knowledge base entries, like a wikipedia page, but linking is unfortunately limited to well-known entities with pre-built pages. This paper asks a more basic question: can aliases be aligned without background knowledge of the entity? Further, can the semantics surrounding alias mentions be used to inform alignments? We describe statistical models that make decisions based on the lexicographic properties of the aliases with their semantic context in a large corpus of tweets. We experiment on a database of Twitter users and their usernames, and present the first human evaluation for this task. Alignment accuracy approaches human performance at 81%, and we show that while lexicographic features are most important, the semantic context of an alias further improves classification accuracy.</abstract>
<identifier type="citekey">mckelvey-etal-2017-aligning</identifier>
<identifier type="doi">10.18653/v1/W17-1104</identifier>
<location>
<url>https://aclanthology.org/W17-1104</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>25</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Entity Names with Online Aliases on Twitter
%A McKelvey, Kevin
%A Goutzounis, Peter
%A da Cruz, Stephen
%A Chambers, Nathanael
%Y Ku, Lun-Wei
%Y Li, Cheng-Te
%S Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F mckelvey-etal-2017-aligning
%X This paper presents new models that automatically align online aliases with their real entity names. Many research applications rely on identifying entity names in text, but people often refer to entities with unexpected nicknames and aliases. For example, The King and King James are aliases for Lebron James, a professional basketball player. Recent work on entity linking attempts to resolve mentions to knowledge base entries, like a wikipedia page, but linking is unfortunately limited to well-known entities with pre-built pages. This paper asks a more basic question: can aliases be aligned without background knowledge of the entity? Further, can the semantics surrounding alias mentions be used to inform alignments? We describe statistical models that make decisions based on the lexicographic properties of the aliases with their semantic context in a large corpus of tweets. We experiment on a database of Twitter users and their usernames, and present the first human evaluation for this task. Alignment accuracy approaches human performance at 81%, and we show that while lexicographic features are most important, the semantic context of an alias further improves classification accuracy.
%R 10.18653/v1/W17-1104
%U https://aclanthology.org/W17-1104
%U https://doi.org/10.18653/v1/W17-1104
%P 25-35
Markdown (Informal)
[Aligning Entity Names with Online Aliases on Twitter](https://aclanthology.org/W17-1104) (McKelvey et al., SocialNLP 2017)
ACL
- Kevin McKelvey, Peter Goutzounis, Stephen da Cruz, and Nathanael Chambers. 2017. Aligning Entity Names with Online Aliases on Twitter. In Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, pages 25–35, Valencia, Spain. Association for Computational Linguistics.