@inproceedings{wang-etal-2006-towards,
title = "Towards Unified {C}hinese Segmentation Algorithm",
author = "Wang, Fu Lee and
Deng, Xiaotie and
Zou, Feng",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/237_pdf.pdf",
abstract = "As Chinese is an ideographic character-based language, the words in the texts are not delimited by spaces. Indexing of Chinese documents is impossible without a proper segmentation algorithm. Many Chinese segmentation algorithms have been proposed in the past. Traditional segmentation algorithms cannot operate without a large dictionary or a large corpus of training data. Nowadays, the Web has become the largest corpus that is ideal for Chinese segmentation. Although the search engines do not segment texts into proper words, they maintain huge databases of documents and frequencies of character sequences in the documents. Their databases are important potential resources for segmentation. In this paper, we propose a segmentation algorithm by mining web data with the help from search engines. It is the first unified segmentation algorithm for Chinese language from different geographical areas. Experiments have been conducted on the datasets of a recent Chinese segmentation competition. The results show that our algorithm outperforms the traditional algorithms in terms of precision and recall. Moreover, our algorithm can effectively deal with the problem of segmentation ambiguity, new word (unknown word) detection, and stop words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2006-towards">
<titleInfo>
<title>Towards Unified Chinese Segmentation Algorithm</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="given">Lee</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaotie</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Chinese is an ideographic character-based language, the words in the texts are not delimited by spaces. Indexing of Chinese documents is impossible without a proper segmentation algorithm. Many Chinese segmentation algorithms have been proposed in the past. Traditional segmentation algorithms cannot operate without a large dictionary or a large corpus of training data. Nowadays, the Web has become the largest corpus that is ideal for Chinese segmentation. Although the search engines do not segment texts into proper words, they maintain huge databases of documents and frequencies of character sequences in the documents. Their databases are important potential resources for segmentation. In this paper, we propose a segmentation algorithm by mining web data with the help from search engines. It is the first unified segmentation algorithm for Chinese language from different geographical areas. Experiments have been conducted on the datasets of a recent Chinese segmentation competition. The results show that our algorithm outperforms the traditional algorithms in terms of precision and recall. Moreover, our algorithm can effectively deal with the problem of segmentation ambiguity, new word (unknown word) detection, and stop words.</abstract>
<identifier type="citekey">wang-etal-2006-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/237_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Unified Chinese Segmentation Algorithm
%A Wang, Fu Lee
%A Deng, Xiaotie
%A Zou, Feng
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F wang-etal-2006-towards
%X As Chinese is an ideographic character-based language, the words in the texts are not delimited by spaces. Indexing of Chinese documents is impossible without a proper segmentation algorithm. Many Chinese segmentation algorithms have been proposed in the past. Traditional segmentation algorithms cannot operate without a large dictionary or a large corpus of training data. Nowadays, the Web has become the largest corpus that is ideal for Chinese segmentation. Although the search engines do not segment texts into proper words, they maintain huge databases of documents and frequencies of character sequences in the documents. Their databases are important potential resources for segmentation. In this paper, we propose a segmentation algorithm by mining web data with the help from search engines. It is the first unified segmentation algorithm for Chinese language from different geographical areas. Experiments have been conducted on the datasets of a recent Chinese segmentation competition. The results show that our algorithm outperforms the traditional algorithms in terms of precision and recall. Moreover, our algorithm can effectively deal with the problem of segmentation ambiguity, new word (unknown word) detection, and stop words.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/237_pdf.pdf
Markdown (Informal)
[Towards Unified Chinese Segmentation Algorithm](http://www.lrec-conf.org/proceedings/lrec2006/pdf/237_pdf.pdf) (Wang et al., LREC 2006)
ACL
- Fu Lee Wang, Xiaotie Deng, and Feng Zou. 2006. Towards Unified Chinese Segmentation Algorithm. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).