@inproceedings{ren-etal-2008-research,
title = "A Research on Automatic {C}hinese Catchword Extraction",
author = "Ren, Han and
Ji, Donghong and
Han, Lei",
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/96_paper.pdf",
abstract = "Catchwords refer to popular words or phrases within certain area in certain period of time. In this paper, we propose a novel approach for automatic Chinese catchwords extraction. At the beginning, we discuss the linguistic definition of catchwords and analyze the features of catchwords by manual evaluation. According to those features of catchwords, we define three aspects to describe Popular Degree of catchwords. To extract terms with maximum meaning, we adopt an effective ATE algorithm for multi-character words and long phrases. Then we use conic fitting in Time Series Analysis to build Popular Degree Curves of extracted terms. To calculate Popular Degree Values of catchwords, a formula is proposed which includes values of Popular Trend, Peak Value and Popular Keeping. Finally, a ranking list of catchword candidates is built according to Popular Degree Values. Experiments show that automatic Chinese catchword extraction is effective and objective in comparison with manual evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2008-research">
<titleInfo>
<title>A Research on Automatic Chinese Catchword Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Han</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>Catchwords refer to popular words or phrases within certain area in certain period of time. In this paper, we propose a novel approach for automatic Chinese catchwords extraction. At the beginning, we discuss the linguistic definition of catchwords and analyze the features of catchwords by manual evaluation. According to those features of catchwords, we define three aspects to describe Popular Degree of catchwords. To extract terms with maximum meaning, we adopt an effective ATE algorithm for multi-character words and long phrases. Then we use conic fitting in Time Series Analysis to build Popular Degree Curves of extracted terms. To calculate Popular Degree Values of catchwords, a formula is proposed which includes values of Popular Trend, Peak Value and Popular Keeping. Finally, a ranking list of catchword candidates is built according to Popular Degree Values. Experiments show that automatic Chinese catchword extraction is effective and objective in comparison with manual evaluation.</abstract>
<identifier type="citekey">ren-etal-2008-research</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/96_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Research on Automatic Chinese Catchword Extraction
%A Ren, Han
%A Ji, Donghong
%A Han, Lei
%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 ren-etal-2008-research
%X Catchwords refer to popular words or phrases within certain area in certain period of time. In this paper, we propose a novel approach for automatic Chinese catchwords extraction. At the beginning, we discuss the linguistic definition of catchwords and analyze the features of catchwords by manual evaluation. According to those features of catchwords, we define three aspects to describe Popular Degree of catchwords. To extract terms with maximum meaning, we adopt an effective ATE algorithm for multi-character words and long phrases. Then we use conic fitting in Time Series Analysis to build Popular Degree Curves of extracted terms. To calculate Popular Degree Values of catchwords, a formula is proposed which includes values of Popular Trend, Peak Value and Popular Keeping. Finally, a ranking list of catchword candidates is built according to Popular Degree Values. Experiments show that automatic Chinese catchword extraction is effective and objective in comparison with manual evaluation.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/96_paper.pdf
Markdown (Informal)
[A Research on Automatic Chinese Catchword Extraction](http://www.lrec-conf.org/proceedings/lrec2008/pdf/96_paper.pdf) (Ren et al., LREC 2008)
ACL
- Han Ren, Donghong Ji, and Lei Han. 2008. A Research on Automatic Chinese Catchword Extraction. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).