@inproceedings{lai-winterstein-2020-cifu,
title = "{C}ifu: a Frequency Lexicon of {H}ong {K}ong {C}antonese",
author = "Lai, Regine and
Winterstein, Gr{\'e}goire",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.375",
pages = "3069--3077",
abstract = "This paper introduces Cifu, a lexical database for Hong Kong Cantonese (HKC) that offers phonological and orthographic information, frequency measures, and lexical neighborhood information for lexical items in HKC. Cifu is of use for NLP applications and the design and analysis of psycholinguistics experiments on HKC. We elaborate on the characteristics and challenges specific to HKC that were relevant in the design of Cifu. This includes lexical, orthographic and phonological aspects of HKC, word segmentation issues, the place of HKC in written media, and the availability of data. We discuss the measure of Neighborhood Density (ND), highlighting how the analytic nature of Cantonese and its writing system affect that measure. We justify using six different variations of ND, based on the possibility of inserting or deleting phonemes when searching for neighbors and on the choice of data for retrieving frequencies. Statistics about the four genres (written, adult spoken, children spoken and child-directed) within the dataset are discussed. We find that the lexical diversity of the child-directed speech genre is particularly low, compared to a size-matched written corpus. The correlations of word frequencies of different genres are all high, but in generally decrease as word length increases.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lai-winterstein-2020-cifu">
<titleInfo>
<title>Cifu: a Frequency Lexicon of Hong Kong Cantonese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regine</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grégoire</namePart>
<namePart type="family">Winterstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper introduces Cifu, a lexical database for Hong Kong Cantonese (HKC) that offers phonological and orthographic information, frequency measures, and lexical neighborhood information for lexical items in HKC. Cifu is of use for NLP applications and the design and analysis of psycholinguistics experiments on HKC. We elaborate on the characteristics and challenges specific to HKC that were relevant in the design of Cifu. This includes lexical, orthographic and phonological aspects of HKC, word segmentation issues, the place of HKC in written media, and the availability of data. We discuss the measure of Neighborhood Density (ND), highlighting how the analytic nature of Cantonese and its writing system affect that measure. We justify using six different variations of ND, based on the possibility of inserting or deleting phonemes when searching for neighbors and on the choice of data for retrieving frequencies. Statistics about the four genres (written, adult spoken, children spoken and child-directed) within the dataset are discussed. We find that the lexical diversity of the child-directed speech genre is particularly low, compared to a size-matched written corpus. The correlations of word frequencies of different genres are all high, but in generally decrease as word length increases.</abstract>
<identifier type="citekey">lai-winterstein-2020-cifu</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.375</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3069</start>
<end>3077</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cifu: a Frequency Lexicon of Hong Kong Cantonese
%A Lai, Regine
%A Winterstein, Grégoire
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F lai-winterstein-2020-cifu
%X This paper introduces Cifu, a lexical database for Hong Kong Cantonese (HKC) that offers phonological and orthographic information, frequency measures, and lexical neighborhood information for lexical items in HKC. Cifu is of use for NLP applications and the design and analysis of psycholinguistics experiments on HKC. We elaborate on the characteristics and challenges specific to HKC that were relevant in the design of Cifu. This includes lexical, orthographic and phonological aspects of HKC, word segmentation issues, the place of HKC in written media, and the availability of data. We discuss the measure of Neighborhood Density (ND), highlighting how the analytic nature of Cantonese and its writing system affect that measure. We justify using six different variations of ND, based on the possibility of inserting or deleting phonemes when searching for neighbors and on the choice of data for retrieving frequencies. Statistics about the four genres (written, adult spoken, children spoken and child-directed) within the dataset are discussed. We find that the lexical diversity of the child-directed speech genre is particularly low, compared to a size-matched written corpus. The correlations of word frequencies of different genres are all high, but in generally decrease as word length increases.
%U https://aclanthology.org/2020.lrec-1.375
%P 3069-3077
Markdown (Informal)
[Cifu: a Frequency Lexicon of Hong Kong Cantonese](https://aclanthology.org/2020.lrec-1.375) (Lai & Winterstein, LREC 2020)
ACL
- Regine Lai and Grégoire Winterstein. 2020. Cifu: a Frequency Lexicon of Hong Kong Cantonese. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3069–3077, Marseille, France. European Language Resources Association.