@inproceedings{peirsman-2006-unsupervised,
title = "Unsupervised approaches to metonymy recognition",
author = "Peirsman, Yves",
editor = "Mertens, Piet and
Fairon, C{\'e}drick and
Dister, Anne and
Watrin, Patrick",
booktitle = "Actes de la 13{\`e}me conf{\'e}rence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues",
month = apr,
year = "2006",
address = "Leuven, Belgique",
publisher = "ATALA",
url = "https://aclanthology.org/2006.jeptalnrecital-recital.7",
pages = "709--718",
abstract = {To this day, the automatic recognition of metonymies has generally been addressed with supervised approaches. However, these require the annotation of a large number of training instances and hence, hinder the development of a wide-scale metonymy recognition system. This paper investigates if this knowledge acquisition bottleneck in metonymy recognition can be resolved by the application of unsupervised learning. Although the investigated technique, Sch{\"u}tze{'}s (1998) algorithm, enjoys considerable popularity in Word Sense Disambiguation, I will show that it is not yet robust enough to tackle the specific case of metonymy recognition. In particular, I will study the influence on its performance of four variables{---}the type of data set, the size of the context window, the application of SVD and the type of feature selection.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peirsman-2006-unsupervised">
<titleInfo>
<title>Unsupervised approaches to metonymy recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Peirsman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 13ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piet</namePart>
<namePart type="family">Mertens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cédrick</namePart>
<namePart type="family">Fairon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Dister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Watrin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA</publisher>
<place>
<placeTerm type="text">Leuven, Belgique</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To this day, the automatic recognition of metonymies has generally been addressed with supervised approaches. However, these require the annotation of a large number of training instances and hence, hinder the development of a wide-scale metonymy recognition system. This paper investigates if this knowledge acquisition bottleneck in metonymy recognition can be resolved by the application of unsupervised learning. Although the investigated technique, Schütze’s (1998) algorithm, enjoys considerable popularity in Word Sense Disambiguation, I will show that it is not yet robust enough to tackle the specific case of metonymy recognition. In particular, I will study the influence on its performance of four variables—the type of data set, the size of the context window, the application of SVD and the type of feature selection.</abstract>
<identifier type="citekey">peirsman-2006-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2006.jeptalnrecital-recital.7</url>
</location>
<part>
<date>2006-04</date>
<extent unit="page">
<start>709</start>
<end>718</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised approaches to metonymy recognition
%A Peirsman, Yves
%Y Mertens, Piet
%Y Fairon, Cédrick
%Y Dister, Anne
%Y Watrin, Patrick
%S Actes de la 13ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues
%D 2006
%8 April
%I ATALA
%C Leuven, Belgique
%F peirsman-2006-unsupervised
%X To this day, the automatic recognition of metonymies has generally been addressed with supervised approaches. However, these require the annotation of a large number of training instances and hence, hinder the development of a wide-scale metonymy recognition system. This paper investigates if this knowledge acquisition bottleneck in metonymy recognition can be resolved by the application of unsupervised learning. Although the investigated technique, Schütze’s (1998) algorithm, enjoys considerable popularity in Word Sense Disambiguation, I will show that it is not yet robust enough to tackle the specific case of metonymy recognition. In particular, I will study the influence on its performance of four variables—the type of data set, the size of the context window, the application of SVD and the type of feature selection.
%U https://aclanthology.org/2006.jeptalnrecital-recital.7
%P 709-718
Markdown (Informal)
[Unsupervised approaches to metonymy recognition](https://aclanthology.org/2006.jeptalnrecital-recital.7) (Peirsman, JEP/TALN/RECITAL 2006)
ACL
- Yves Peirsman. 2006. Unsupervised approaches to metonymy recognition. In Actes de la 13ème conférence sur le Traitement Automatique des Langues Naturelles. REncontres jeunes Chercheurs en Informatique pour le Traitement Automatique des Langues, pages 709–718, Leuven, Belgique. ATALA.