@inproceedings{neergaard-etal-2016-database,
title = "Database of {M}andarin Neighborhood Statistics",
author = "Neergaard, Karl and
Xu, Hongzhi and
Huang, Chu-Ren",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1636",
pages = "4032--4036",
abstract = "In the design of controlled experiments with language stimuli, researchers from psycholinguistic, neurolinguistic, and related fields, require language resources that isolate variables known to affect language processing. This article describes a freely available database that provides word level statistics for words and nonwords of Mandarin, Chinese. The featured lexical statistics include subtitle corpus frequency, phonological neighborhood density, neighborhood frequency, and homophone density. The accompanying word descriptors include pinyin, ascii phonetic transcription (sampa), lexical tone, syllable structure, dominant PoS, and syllable, segment and pinyin lengths for each phonological word. It is designed for researchers particularly concerned with language processing of isolated words and made to accommodate multiple existing hypotheses concerning the structure of the Mandarin syllable. The database is divided into multiple files according to the desired search criteria: 1) the syllable segmentation schema used to calculate density measures, and 2) whether the search is for words or nonwords. The database is open to the research community at \url{https://github.com/karlneergaard/Mandarin-Neighborhood-Statistics}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="neergaard-etal-2016-database">
<titleInfo>
<title>Database of Mandarin Neighborhood Statistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="family">Neergaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhi</namePart>
<namePart type="family">Xu</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>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the design of controlled experiments with language stimuli, researchers from psycholinguistic, neurolinguistic, and related fields, require language resources that isolate variables known to affect language processing. This article describes a freely available database that provides word level statistics for words and nonwords of Mandarin, Chinese. The featured lexical statistics include subtitle corpus frequency, phonological neighborhood density, neighborhood frequency, and homophone density. The accompanying word descriptors include pinyin, ascii phonetic transcription (sampa), lexical tone, syllable structure, dominant PoS, and syllable, segment and pinyin lengths for each phonological word. It is designed for researchers particularly concerned with language processing of isolated words and made to accommodate multiple existing hypotheses concerning the structure of the Mandarin syllable. The database is divided into multiple files according to the desired search criteria: 1) the syllable segmentation schema used to calculate density measures, and 2) whether the search is for words or nonwords. The database is open to the research community at https://github.com/karlneergaard/Mandarin-Neighborhood-Statistics.</abstract>
<identifier type="citekey">neergaard-etal-2016-database</identifier>
<location>
<url>https://aclanthology.org/L16-1636</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4032</start>
<end>4036</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Database of Mandarin Neighborhood Statistics
%A Neergaard, Karl
%A Xu, Hongzhi
%A Huang, Chu-Ren
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F neergaard-etal-2016-database
%X In the design of controlled experiments with language stimuli, researchers from psycholinguistic, neurolinguistic, and related fields, require language resources that isolate variables known to affect language processing. This article describes a freely available database that provides word level statistics for words and nonwords of Mandarin, Chinese. The featured lexical statistics include subtitle corpus frequency, phonological neighborhood density, neighborhood frequency, and homophone density. The accompanying word descriptors include pinyin, ascii phonetic transcription (sampa), lexical tone, syllable structure, dominant PoS, and syllable, segment and pinyin lengths for each phonological word. It is designed for researchers particularly concerned with language processing of isolated words and made to accommodate multiple existing hypotheses concerning the structure of the Mandarin syllable. The database is divided into multiple files according to the desired search criteria: 1) the syllable segmentation schema used to calculate density measures, and 2) whether the search is for words or nonwords. The database is open to the research community at https://github.com/karlneergaard/Mandarin-Neighborhood-Statistics.
%U https://aclanthology.org/L16-1636
%P 4032-4036
Markdown (Informal)
[Database of Mandarin Neighborhood Statistics](https://aclanthology.org/L16-1636) (Neergaard et al., LREC 2016)
ACL
- Karl Neergaard, Hongzhi Xu, and Chu-Ren Huang. 2016. Database of Mandarin Neighborhood Statistics. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4032–4036, Portorož, Slovenia. European Language Resources Association (ELRA).