@inproceedings{sagot-fiser-2012-cleaning,
title = "Cleaning noisy wordnets",
author = "Sagot, Beno{\^\i}t and
Fi{\v{s}}er, Darja",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1127_Paper.pdf",
pages = "3468--3472",
abstract = "Automatic approaches to creating and extending wordnets, which have become very popular in the past decade, inadvertently result in noisy synsets. This is why we propose an approach to detect synset outliers in order to eliminate the noise and improve accuracy of the developed wordnets, so that they become more useful lexico-semantic resources for natural language applications. The approach compares the words that appear in the synset and its surroundings with the contexts of the literals in question they are used in based on large monolingual corpora. By fine-tuning the outlier threshold we can influence how many outlier candidates will be eliminated. Although the proposed approach is language-independent we test it on Slovene and French that were created automatically from bilingual resources and contain plenty of disambiguation errors. Manual evaluation of the results shows that by applying a threshold similar to the estimated error rate in the respective wordnets, 67{\%} of the proposed outlier candidates are indeed incorrect for French and a 64{\%} for Slovene. This is a big improvement compared to the estimated overall error rates in the resources, which are 12{\%} for French and 15{\%} for Slovene.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sagot-fiser-2012-cleaning">
<titleInfo>
<title>Cleaning noisy wordnets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic approaches to creating and extending wordnets, which have become very popular in the past decade, inadvertently result in noisy synsets. This is why we propose an approach to detect synset outliers in order to eliminate the noise and improve accuracy of the developed wordnets, so that they become more useful lexico-semantic resources for natural language applications. The approach compares the words that appear in the synset and its surroundings with the contexts of the literals in question they are used in based on large monolingual corpora. By fine-tuning the outlier threshold we can influence how many outlier candidates will be eliminated. Although the proposed approach is language-independent we test it on Slovene and French that were created automatically from bilingual resources and contain plenty of disambiguation errors. Manual evaluation of the results shows that by applying a threshold similar to the estimated error rate in the respective wordnets, 67% of the proposed outlier candidates are indeed incorrect for French and a 64% for Slovene. This is a big improvement compared to the estimated overall error rates in the resources, which are 12% for French and 15% for Slovene.</abstract>
<identifier type="citekey">sagot-fiser-2012-cleaning</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1127_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3468</start>
<end>3472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cleaning noisy wordnets
%A Sagot, Benoît
%A Fišer, Darja
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F sagot-fiser-2012-cleaning
%X Automatic approaches to creating and extending wordnets, which have become very popular in the past decade, inadvertently result in noisy synsets. This is why we propose an approach to detect synset outliers in order to eliminate the noise and improve accuracy of the developed wordnets, so that they become more useful lexico-semantic resources for natural language applications. The approach compares the words that appear in the synset and its surroundings with the contexts of the literals in question they are used in based on large monolingual corpora. By fine-tuning the outlier threshold we can influence how many outlier candidates will be eliminated. Although the proposed approach is language-independent we test it on Slovene and French that were created automatically from bilingual resources and contain plenty of disambiguation errors. Manual evaluation of the results shows that by applying a threshold similar to the estimated error rate in the respective wordnets, 67% of the proposed outlier candidates are indeed incorrect for French and a 64% for Slovene. This is a big improvement compared to the estimated overall error rates in the resources, which are 12% for French and 15% for Slovene.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1127_Paper.pdf
%P 3468-3472
Markdown (Informal)
[Cleaning noisy wordnets](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1127_Paper.pdf) (Sagot & Fišer, LREC 2012)
ACL
- Benoît Sagot and Darja Fišer. 2012. Cleaning noisy wordnets. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3468–3472, Istanbul, Turkey. European Language Resources Association (ELRA).