@inproceedings{yang-etal-2008-chinese-term,
title = "{C}hinese Term Extraction Based on Delimiters",
author = "Yang, Yuhang and
Lu, Qin and
Zhao, Tiejun",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/72_paper.pdf",
abstract = "Existing techniques extract term candidates by looking for internal and contextual information associated with domain specific terms. The algorithms always face the dilemma that fewer features are not enough to distinguish terms from non-terms whereas more features lead to more conflicts among selected features. This paper presents a novel approach for term extraction based on delimiters which are much more stable and domain independent. The proposed approach is not as sensitive to term frequency as that of previous works. This approach has no strict limit or hard rules and thus they can deal with all kinds of terms. It also requires no prior domain knowledge and no additional training to adapt to new domains. Consequently, the proposed approach can be applied to different domains easily and it is especially useful for resource-limited domains. Evaluations conducted on two different domains for Chinese term extraction show significant improvements over existing techniques which verifies its efficiency and domain independent nature. Experiments on new term extraction indicate that the proposed approach can also serve as an effective tool for domain lexicon expansion.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2008-chinese-term">
<titleInfo>
<title>Chinese Term Extraction Based on Delimiters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiejun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing techniques extract term candidates by looking for internal and contextual information associated with domain specific terms. The algorithms always face the dilemma that fewer features are not enough to distinguish terms from non-terms whereas more features lead to more conflicts among selected features. This paper presents a novel approach for term extraction based on delimiters which are much more stable and domain independent. The proposed approach is not as sensitive to term frequency as that of previous works. This approach has no strict limit or hard rules and thus they can deal with all kinds of terms. It also requires no prior domain knowledge and no additional training to adapt to new domains. Consequently, the proposed approach can be applied to different domains easily and it is especially useful for resource-limited domains. Evaluations conducted on two different domains for Chinese term extraction show significant improvements over existing techniques which verifies its efficiency and domain independent nature. Experiments on new term extraction indicate that the proposed approach can also serve as an effective tool for domain lexicon expansion.</abstract>
<identifier type="citekey">yang-etal-2008-chinese-term</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/72_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chinese Term Extraction Based on Delimiters
%A Yang, Yuhang
%A Lu, Qin
%A Zhao, Tiejun
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F yang-etal-2008-chinese-term
%X Existing techniques extract term candidates by looking for internal and contextual information associated with domain specific terms. The algorithms always face the dilemma that fewer features are not enough to distinguish terms from non-terms whereas more features lead to more conflicts among selected features. This paper presents a novel approach for term extraction based on delimiters which are much more stable and domain independent. The proposed approach is not as sensitive to term frequency as that of previous works. This approach has no strict limit or hard rules and thus they can deal with all kinds of terms. It also requires no prior domain knowledge and no additional training to adapt to new domains. Consequently, the proposed approach can be applied to different domains easily and it is especially useful for resource-limited domains. Evaluations conducted on two different domains for Chinese term extraction show significant improvements over existing techniques which verifies its efficiency and domain independent nature. Experiments on new term extraction indicate that the proposed approach can also serve as an effective tool for domain lexicon expansion.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/72_paper.pdf
Markdown (Informal)
[Chinese Term Extraction Based on Delimiters](http://www.lrec-conf.org/proceedings/lrec2008/pdf/72_paper.pdf) (Yang et al., LREC 2008)
ACL
- Yuhang Yang, Qin Lu, and Tiejun Zhao. 2008. Chinese Term Extraction Based on Delimiters. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).