@inproceedings{jurgens-2014-analysis,
title = "An analysis of ambiguity in word sense annotations",
author = "Jurgens, David",
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/904_Paper.pdf",
pages = "3006--3012",
abstract = "Word sense annotation is a challenging task where annotators distinguish which meaning of a word is present in a given context. In some contexts, a word usage may elicit multiple interpretations, resulting either in annotators disagreeing or in allowing the usage to be annotated with multiple senses. While some works have allowed the latter, the extent to which multiple sense annotations are needed has not been assessed. The present work analyzes a dataset of instances annotated with multiple WordNet senses to assess the causes of the multiple interpretations and their relative frequencies, along with the effect of the multiple senses on the contextual interpretation. We show that contextual underspecification is the primary cause of multiple interpretations but that syllepsis still accounts for more than a third of the cases. In addition, we show that sense coarsening can only partially remove the need for labeling instances with multiple senses and we provide suggestions for how future sense annotation guidelines might be developed to account for this need.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jurgens-2014-analysis">
<titleInfo>
<title>An analysis of ambiguity in word sense annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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>Word sense annotation is a challenging task where annotators distinguish which meaning of a word is present in a given context. In some contexts, a word usage may elicit multiple interpretations, resulting either in annotators disagreeing or in allowing the usage to be annotated with multiple senses. While some works have allowed the latter, the extent to which multiple sense annotations are needed has not been assessed. The present work analyzes a dataset of instances annotated with multiple WordNet senses to assess the causes of the multiple interpretations and their relative frequencies, along with the effect of the multiple senses on the contextual interpretation. We show that contextual underspecification is the primary cause of multiple interpretations but that syllepsis still accounts for more than a third of the cases. In addition, we show that sense coarsening can only partially remove the need for labeling instances with multiple senses and we provide suggestions for how future sense annotation guidelines might be developed to account for this need.</abstract>
<identifier type="citekey">jurgens-2014-analysis</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/904_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3006</start>
<end>3012</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An analysis of ambiguity in word sense annotations
%A Jurgens, David
%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 jurgens-2014-analysis
%X Word sense annotation is a challenging task where annotators distinguish which meaning of a word is present in a given context. In some contexts, a word usage may elicit multiple interpretations, resulting either in annotators disagreeing or in allowing the usage to be annotated with multiple senses. While some works have allowed the latter, the extent to which multiple sense annotations are needed has not been assessed. The present work analyzes a dataset of instances annotated with multiple WordNet senses to assess the causes of the multiple interpretations and their relative frequencies, along with the effect of the multiple senses on the contextual interpretation. We show that contextual underspecification is the primary cause of multiple interpretations but that syllepsis still accounts for more than a third of the cases. In addition, we show that sense coarsening can only partially remove the need for labeling instances with multiple senses and we provide suggestions for how future sense annotation guidelines might be developed to account for this need.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/904_Paper.pdf
%P 3006-3012
Markdown (Informal)
[An analysis of ambiguity in word sense annotations](http://www.lrec-conf.org/proceedings/lrec2014/pdf/904_Paper.pdf) (Jurgens, LREC 2014)
ACL
- David Jurgens. 2014. An analysis of ambiguity in word sense annotations. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3006–3012, Reykjavik, Iceland. European Language Resources Association (ELRA).