@inproceedings{wang-etal-2010-automatic,
title = "Automatic Acquisition of {C}hinese Novel Noun Compounds",
author = "Wang, Meng and
Huang, Chu-Ren and
Yu, Shiwen and
Sun, Weiwei",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/377_Paper.pdf",
abstract = "Automatic acquisition of novel compounds is notoriously difficult because most novel compounds have relatively low frequency in a corpus. The current study proposes a new method to deal with the novel compound acquisition challenge. We model this task as a two-class classification problem in which a candidate compound is either classified as a compound or a non-compound. A machine learning method using SVM, incorporating two types of linguistically motivated features: semantic features and character features, is applied to identify rare but valid noun compounds. We explore two kinds of training data: one is virtual training data which is obtained by three statistical scores, i.e. co-occurrence frequency, mutual information and dependent ratio, from the frequent compounds; the other is real training data which is randomly selected from the infrequent compounds. We conduct comparative experiments, and the experimental results show that even with limited direct evidence in the corpus for the novel compounds, we can make full use of the typical frequent compounds to help in the discovery of the novel compounds.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2010-automatic">
<titleInfo>
<title>Automatic Acquisition of Chinese Novel Noun Compounds</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiwen</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiwei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic acquisition of novel compounds is notoriously difficult because most novel compounds have relatively low frequency in a corpus. The current study proposes a new method to deal with the novel compound acquisition challenge. We model this task as a two-class classification problem in which a candidate compound is either classified as a compound or a non-compound. A machine learning method using SVM, incorporating two types of linguistically motivated features: semantic features and character features, is applied to identify rare but valid noun compounds. We explore two kinds of training data: one is virtual training data which is obtained by three statistical scores, i.e. co-occurrence frequency, mutual information and dependent ratio, from the frequent compounds; the other is real training data which is randomly selected from the infrequent compounds. We conduct comparative experiments, and the experimental results show that even with limited direct evidence in the corpus for the novel compounds, we can make full use of the typical frequent compounds to help in the discovery of the novel compounds.</abstract>
<identifier type="citekey">wang-etal-2010-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/377_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Acquisition of Chinese Novel Noun Compounds
%A Wang, Meng
%A Huang, Chu-Ren
%A Yu, Shiwen
%A Sun, Weiwei
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F wang-etal-2010-automatic
%X Automatic acquisition of novel compounds is notoriously difficult because most novel compounds have relatively low frequency in a corpus. The current study proposes a new method to deal with the novel compound acquisition challenge. We model this task as a two-class classification problem in which a candidate compound is either classified as a compound or a non-compound. A machine learning method using SVM, incorporating two types of linguistically motivated features: semantic features and character features, is applied to identify rare but valid noun compounds. We explore two kinds of training data: one is virtual training data which is obtained by three statistical scores, i.e. co-occurrence frequency, mutual information and dependent ratio, from the frequent compounds; the other is real training data which is randomly selected from the infrequent compounds. We conduct comparative experiments, and the experimental results show that even with limited direct evidence in the corpus for the novel compounds, we can make full use of the typical frequent compounds to help in the discovery of the novel compounds.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/377_Paper.pdf
Markdown (Informal)
[Automatic Acquisition of Chinese Novel Noun Compounds](http://www.lrec-conf.org/proceedings/lrec2010/pdf/377_Paper.pdf) (Wang et al., LREC 2010)
ACL
- Meng Wang, Chu-Ren Huang, Shiwen Yu, and Weiwei Sun. 2010. Automatic Acquisition of Chinese Novel Noun Compounds. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).