@inproceedings{murawaki-kurohashi-2010-online,
title = "Online {J}apanese Unknown Morpheme Detection using Orthographic Variation",
author = "Murawaki, Yugo and
Kurohashi, Sadao",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/171_Paper.pdf",
abstract = "To solve the unknown morpheme problem in Japanese morphological analysis, we previously proposed a novel framework of online unknown morpheme acquisition and its implementation. This framework poses a previously unexplored problem, online unknown morpheme detection. Online unknown morpheme detection is a task of finding morphemes in each sentence that are not listed in a given lexicon. Unlike in English, it is a non-trivial task because Japanese does not delimit words by white space. We first present a baseline method that simply uses the output of the morphological analyzer. We then show that it fails to detect some unknown morphemes because they are over-segmented into shorter registered morphemes. To cope with this problem, we present a simple solution, the use of orthographic variation of Japanese. Under the assumption that orthographic variants behave similarly, each over-segmentation candidate is checked against its counterparts. Experiments show that the proposed method improves the recall of detection and contributes to improving unknown morpheme acquisition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="murawaki-kurohashi-2010-online">
<titleInfo>
<title>Online Japanese Unknown Morpheme Detection using Orthographic Variation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yugo</namePart>
<namePart type="family">Murawaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To solve the unknown morpheme problem in Japanese morphological analysis, we previously proposed a novel framework of online unknown morpheme acquisition and its implementation. This framework poses a previously unexplored problem, online unknown morpheme detection. Online unknown morpheme detection is a task of finding morphemes in each sentence that are not listed in a given lexicon. Unlike in English, it is a non-trivial task because Japanese does not delimit words by white space. We first present a baseline method that simply uses the output of the morphological analyzer. We then show that it fails to detect some unknown morphemes because they are over-segmented into shorter registered morphemes. To cope with this problem, we present a simple solution, the use of orthographic variation of Japanese. Under the assumption that orthographic variants behave similarly, each over-segmentation candidate is checked against its counterparts. Experiments show that the proposed method improves the recall of detection and contributes to improving unknown morpheme acquisition.</abstract>
<identifier type="citekey">murawaki-kurohashi-2010-online</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/171_Paper.pdf</url>
</location>
<part>
<date>2010-may</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Online Japanese Unknown Morpheme Detection using Orthographic Variation
%A Murawaki, Yugo
%A Kurohashi, Sadao
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 may
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F murawaki-kurohashi-2010-online
%X To solve the unknown morpheme problem in Japanese morphological analysis, we previously proposed a novel framework of online unknown morpheme acquisition and its implementation. This framework poses a previously unexplored problem, online unknown morpheme detection. Online unknown morpheme detection is a task of finding morphemes in each sentence that are not listed in a given lexicon. Unlike in English, it is a non-trivial task because Japanese does not delimit words by white space. We first present a baseline method that simply uses the output of the morphological analyzer. We then show that it fails to detect some unknown morphemes because they are over-segmented into shorter registered morphemes. To cope with this problem, we present a simple solution, the use of orthographic variation of Japanese. Under the assumption that orthographic variants behave similarly, each over-segmentation candidate is checked against its counterparts. Experiments show that the proposed method improves the recall of detection and contributes to improving unknown morpheme acquisition.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/171_Paper.pdf
Markdown (Informal)
[Online Japanese Unknown Morpheme Detection using Orthographic Variation](http://www.lrec-conf.org/proceedings/lrec2010/pdf/171_Paper.pdf) (Murawaki & Kurohashi, LREC 2010)
ACL