@inproceedings{ma-2014-automatic,
title = "Automatic Refinement of Syntactic Categories in {C}hinese Word Structures",
author = "Ma, Jianqiang",
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/1158_Paper.pdf",
pages = "4087--4092",
abstract = "Annotated word structures are useful for various Chinese NLP tasks, such as word segmentation, POS tagging and syntactic parsing. Chinese word structures are often represented by binary trees, the nodes of which are labeled with syntactic categories, due to the syntactic nature of Chinese word formation. It is desirable to refine the annotation by labeling nodes of word structure trees with more proper syntactic categories so that the combinatorial properties in the word formation process are better captured. This can lead to improved performances on the tasks that exploit word structure annotations. We propose syntactically inspired algorithms to automatically induce syntactic categories of word structure trees using POS tagged corpus and branching in existing Chinese word structure trees. We evaluate the quality of our annotation by comparing the performances of models based on our annotation and another publicly available annotation, respectively. The results on two variations of Chinese word segmentation task show that using our annotation can lead to significant performance improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-2014-automatic">
<titleInfo>
<title>Automatic Refinement of Syntactic Categories in Chinese Word Structures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianqiang</namePart>
<namePart type="family">Ma</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>Annotated word structures are useful for various Chinese NLP tasks, such as word segmentation, POS tagging and syntactic parsing. Chinese word structures are often represented by binary trees, the nodes of which are labeled with syntactic categories, due to the syntactic nature of Chinese word formation. It is desirable to refine the annotation by labeling nodes of word structure trees with more proper syntactic categories so that the combinatorial properties in the word formation process are better captured. This can lead to improved performances on the tasks that exploit word structure annotations. We propose syntactically inspired algorithms to automatically induce syntactic categories of word structure trees using POS tagged corpus and branching in existing Chinese word structure trees. We evaluate the quality of our annotation by comparing the performances of models based on our annotation and another publicly available annotation, respectively. The results on two variations of Chinese word segmentation task show that using our annotation can lead to significant performance improvements.</abstract>
<identifier type="citekey">ma-2014-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1158_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4087</start>
<end>4092</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Refinement of Syntactic Categories in Chinese Word Structures
%A Ma, Jianqiang
%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 ma-2014-automatic
%X Annotated word structures are useful for various Chinese NLP tasks, such as word segmentation, POS tagging and syntactic parsing. Chinese word structures are often represented by binary trees, the nodes of which are labeled with syntactic categories, due to the syntactic nature of Chinese word formation. It is desirable to refine the annotation by labeling nodes of word structure trees with more proper syntactic categories so that the combinatorial properties in the word formation process are better captured. This can lead to improved performances on the tasks that exploit word structure annotations. We propose syntactically inspired algorithms to automatically induce syntactic categories of word structure trees using POS tagged corpus and branching in existing Chinese word structure trees. We evaluate the quality of our annotation by comparing the performances of models based on our annotation and another publicly available annotation, respectively. The results on two variations of Chinese word segmentation task show that using our annotation can lead to significant performance improvements.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1158_Paper.pdf
%P 4087-4092
Markdown (Informal)
[Automatic Refinement of Syntactic Categories in Chinese Word Structures](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1158_Paper.pdf) (Ma, LREC 2014)
ACL