@inproceedings{li-etal-2014-comparison,
title = "Comparison of the Impact of Word Segmentation on Name Tagging for {C}hinese and {J}apanese",
author = "Li, Haibo and
Hagiwara, Masato and
Li, Qi and
Ji, Heng",
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/358_Paper.pdf",
pages = "2532--2536",
abstract = "Word Segmentation is usually considered an essential step for many Chinese and Japanese Natural Language Processing tasks, such as name tagging. This paper presents several new observations and analysis on the impact of word segmentation on name tagging; (1). Due to the limitation of current state-of-the-art Chinese word segmentation performance, a character-based name tagger can outperform its word-based counterparts for Chinese but not for Japanese; (2). It is crucial to keep segmentation settings (e.g. definitions, specifications, methods) consistent between training and testing for name tagging; (3). As long as (2) is ensured, the performance of word segmentation does not have appreciable impact on Chinese and Japanese name tagging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2014-comparison">
<titleInfo>
<title>Comparison of the Impact of Word Segmentation on Name Tagging for Chinese and Japanese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haibo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Hagiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</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 Segmentation is usually considered an essential step for many Chinese and Japanese Natural Language Processing tasks, such as name tagging. This paper presents several new observations and analysis on the impact of word segmentation on name tagging; (1). Due to the limitation of current state-of-the-art Chinese word segmentation performance, a character-based name tagger can outperform its word-based counterparts for Chinese but not for Japanese; (2). It is crucial to keep segmentation settings (e.g. definitions, specifications, methods) consistent between training and testing for name tagging; (3). As long as (2) is ensured, the performance of word segmentation does not have appreciable impact on Chinese and Japanese name tagging.</abstract>
<identifier type="citekey">li-etal-2014-comparison</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/358_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2532</start>
<end>2536</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparison of the Impact of Word Segmentation on Name Tagging for Chinese and Japanese
%A Li, Haibo
%A Hagiwara, Masato
%A Li, Qi
%A Ji, Heng
%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 li-etal-2014-comparison
%X Word Segmentation is usually considered an essential step for many Chinese and Japanese Natural Language Processing tasks, such as name tagging. This paper presents several new observations and analysis on the impact of word segmentation on name tagging; (1). Due to the limitation of current state-of-the-art Chinese word segmentation performance, a character-based name tagger can outperform its word-based counterparts for Chinese but not for Japanese; (2). It is crucial to keep segmentation settings (e.g. definitions, specifications, methods) consistent between training and testing for name tagging; (3). As long as (2) is ensured, the performance of word segmentation does not have appreciable impact on Chinese and Japanese name tagging.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/358_Paper.pdf
%P 2532-2536
Markdown (Informal)
[Comparison of the Impact of Word Segmentation on Name Tagging for Chinese and Japanese](http://www.lrec-conf.org/proceedings/lrec2014/pdf/358_Paper.pdf) (Li et al., LREC 2014)
ACL