@inproceedings{sasaki-shinnou-2012-detection,
title = "Detection of Peculiar Word Sense by Distance Metric Learning with Labeled Examples",
author = "Sasaki, Minoru and
Shinnou, Hiroyuki",
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 = "https://aclanthology.org/L12-1327/",
pages = "601--604",
abstract = "For natural language processing on machines, resolving such peculiar usages would be particularly useful in constructing a dictionary and dataset for word sense disambiguation. Hence, it is necessary to develop a method to detect such peculiar examples of a target word from a corpus. Note that, hereinafter, we define a peculiar example as an instance in which the target word or phrase has a new meaning. In this paper, we proposed a new peculiar example detection method using distance metric learning from labeled example pairs. In this method, first, distance metric learning is performed by large margin nearest neighbor classification for the training data, and new training data points are generated using the distance metric in the original space. Then, peculiar examples are extracted using the local outlier factor, which is a density-based outlier detection method, from the updated training and test data. The efficiency of the proposed method was evaluated on an artificial dataset and the Semeval-2010 Japanese WSD task dataset. The results showed that the proposed method has the highest number of properly detected instances and the highest F-measure value. This shows that the label information of training data is effective for density-based peculiar example detection. Moreover, an experiment on outlier detection using a classification method such as SVM showed that it is difficult to apply the classification method to outlier detection."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sasaki-shinnou-2012-detection">
<titleInfo>
<title>Detection of Peculiar Word Sense by Distance Metric Learning with Labeled Examples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minoru</namePart>
<namePart type="family">Sasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Shinnou</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>For natural language processing on machines, resolving such peculiar usages would be particularly useful in constructing a dictionary and dataset for word sense disambiguation. Hence, it is necessary to develop a method to detect such peculiar examples of a target word from a corpus. Note that, hereinafter, we define a peculiar example as an instance in which the target word or phrase has a new meaning. In this paper, we proposed a new peculiar example detection method using distance metric learning from labeled example pairs. In this method, first, distance metric learning is performed by large margin nearest neighbor classification for the training data, and new training data points are generated using the distance metric in the original space. Then, peculiar examples are extracted using the local outlier factor, which is a density-based outlier detection method, from the updated training and test data. The efficiency of the proposed method was evaluated on an artificial dataset and the Semeval-2010 Japanese WSD task dataset. The results showed that the proposed method has the highest number of properly detected instances and the highest F-measure value. This shows that the label information of training data is effective for density-based peculiar example detection. Moreover, an experiment on outlier detection using a classification method such as SVM showed that it is difficult to apply the classification method to outlier detection.</abstract>
<identifier type="citekey">sasaki-shinnou-2012-detection</identifier>
<location>
<url>https://aclanthology.org/L12-1327/</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>601</start>
<end>604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detection of Peculiar Word Sense by Distance Metric Learning with Labeled Examples
%A Sasaki, Minoru
%A Shinnou, Hiroyuki
%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 sasaki-shinnou-2012-detection
%X For natural language processing on machines, resolving such peculiar usages would be particularly useful in constructing a dictionary and dataset for word sense disambiguation. Hence, it is necessary to develop a method to detect such peculiar examples of a target word from a corpus. Note that, hereinafter, we define a peculiar example as an instance in which the target word or phrase has a new meaning. In this paper, we proposed a new peculiar example detection method using distance metric learning from labeled example pairs. In this method, first, distance metric learning is performed by large margin nearest neighbor classification for the training data, and new training data points are generated using the distance metric in the original space. Then, peculiar examples are extracted using the local outlier factor, which is a density-based outlier detection method, from the updated training and test data. The efficiency of the proposed method was evaluated on an artificial dataset and the Semeval-2010 Japanese WSD task dataset. The results showed that the proposed method has the highest number of properly detected instances and the highest F-measure value. This shows that the label information of training data is effective for density-based peculiar example detection. Moreover, an experiment on outlier detection using a classification method such as SVM showed that it is difficult to apply the classification method to outlier detection.
%U https://aclanthology.org/L12-1327/
%P 601-604
Markdown (Informal)
[Detection of Peculiar Word Sense by Distance Metric Learning with Labeled Examples](https://aclanthology.org/L12-1327/) (Sasaki & Shinnou, LREC 2012)
ACL