@inproceedings{togia-copestake-2014-tagntext,
title = "{T}ag{NT}ext: A parallel corpus for the induction of resource-specific non-taxonomical relations from tagged images",
author = "Togia, Theodosia and
Copestake, Ann",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/738_Paper.pdf",
pages = "3448--3455",
abstract = "When producing textual descriptions, humans express propositions regarding an object; but what do they express when annotating a document with simple tags? To answer this question, we have studied what users of tagging systems would have said if they were to describe a resource with fully fledged text. In particular, our work attempts to answer the following questions: if users were to use full descriptions, would their current tags be words present in these hypothetical sentences? If yes, what kind of language would connect these words? Such questions, although central to the problem of extracting binary relations between tags, have been sidestepped in the existing literature, which has focused on a small subset of possible inter-tag relations, namely hierarchical ones (e.g. {``}car{''} {--}is-a{--} {``}vehicle{''}), as opposed to non-taxonomical relations (e.g. {``}woman{''} {--}wears{--} {``}hat{''}). TagNText is the first attempt to construct a parallel corpus of tags and textual descriptions with respect to particular resources. The corpus provides enough data for the researcher to gain an insight into the nature of underlying relations, as well as the tools and methodology for constructing larger-scale parallel corpora that can aid non-taxonomical relation extraction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="togia-copestake-2014-tagntext">
<titleInfo>
<title>TagNText: A parallel corpus for the induction of resource-specific non-taxonomical relations from tagged images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Theodosia</namePart>
<namePart type="family">Togia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Copestake</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When producing textual descriptions, humans express propositions regarding an object; but what do they express when annotating a document with simple tags? To answer this question, we have studied what users of tagging systems would have said if they were to describe a resource with fully fledged text. In particular, our work attempts to answer the following questions: if users were to use full descriptions, would their current tags be words present in these hypothetical sentences? If yes, what kind of language would connect these words? Such questions, although central to the problem of extracting binary relations between tags, have been sidestepped in the existing literature, which has focused on a small subset of possible inter-tag relations, namely hierarchical ones (e.g. “car” –is-a– “vehicle”), as opposed to non-taxonomical relations (e.g. “woman” –wears– “hat”). TagNText is the first attempt to construct a parallel corpus of tags and textual descriptions with respect to particular resources. The corpus provides enough data for the researcher to gain an insight into the nature of underlying relations, as well as the tools and methodology for constructing larger-scale parallel corpora that can aid non-taxonomical relation extraction.</abstract>
<identifier type="citekey">togia-copestake-2014-tagntext</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/738_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3448</start>
<end>3455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TagNText: A parallel corpus for the induction of resource-specific non-taxonomical relations from tagged images
%A Togia, Theodosia
%A Copestake, Ann
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F togia-copestake-2014-tagntext
%X When producing textual descriptions, humans express propositions regarding an object; but what do they express when annotating a document with simple tags? To answer this question, we have studied what users of tagging systems would have said if they were to describe a resource with fully fledged text. In particular, our work attempts to answer the following questions: if users were to use full descriptions, would their current tags be words present in these hypothetical sentences? If yes, what kind of language would connect these words? Such questions, although central to the problem of extracting binary relations between tags, have been sidestepped in the existing literature, which has focused on a small subset of possible inter-tag relations, namely hierarchical ones (e.g. “car” –is-a– “vehicle”), as opposed to non-taxonomical relations (e.g. “woman” –wears– “hat”). TagNText is the first attempt to construct a parallel corpus of tags and textual descriptions with respect to particular resources. The corpus provides enough data for the researcher to gain an insight into the nature of underlying relations, as well as the tools and methodology for constructing larger-scale parallel corpora that can aid non-taxonomical relation extraction.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/738_Paper.pdf
%P 3448-3455
Markdown (Informal)
[TagNText: A parallel corpus for the induction of resource-specific non-taxonomical relations from tagged images](http://www.lrec-conf.org/proceedings/lrec2014/pdf/738_Paper.pdf) (Togia & Copestake, LREC 2014)
ACL