@inproceedings{lau-etal-2022-words,
title = "Words.hk: A Comprehensive {C}antonese Dictionary Dataset with Definitions, Translations and Transliterated Examples",
author = "Lau, Chaak-ming and
Chan, Grace Wing-yan and
Tse, Raymond Ka-wai and
Chan, Lilian Suet-ying",
editor = {S{\"a}lev{\"a}, Jonne and
Lignos, Constantine},
booktitle = "Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.dclrl-1.7",
pages = "53--62",
abstract = "This paper discusses the compilation of the words.hk Cantonese dictionary dataset, which was compiled through manual annotation over a period of 7 years. Cantonese is a low-resource language with limited tagged or manually checked resources, especially at the sentential level, and this dataset is an attempt to fill the gap. The dataset contains over 53,000 entries of Cantonese words, which comes with basic lexical information (Jyutping phonemic transcription, part-of-speech tags, usage tags), manually crafted definitions in Written Cantonese, English translations, and Cantonese examples with English translation and Jyutping transliterations. Special attention has been paid to handle character variants, so that unintended {``}character errors{''} (equivalent to typos in phonemic writing systems) are filtered out, and intra-speaker variants are handled. Fine details on word segmentation, character variant handling, definition crafting will be discussed. The dataset can be used in a wide range of natural language processing tasks, such as word segmentation, construction of semantic web and training of models for Cantonese transliteration.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lau-etal-2022-words">
<titleInfo>
<title>Words.hk: A Comprehensive Cantonese Dictionary Dataset with Definitions, Translations and Transliterated Examples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaak-ming</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grace</namePart>
<namePart type="given">Wing-yan</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="given">Ka-wai</namePart>
<namePart type="family">Tse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilian</namePart>
<namePart type="given">Suet-ying</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonne</namePart>
<namePart type="family">Sälevä</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</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>
</relatedItem>
<abstract>This paper discusses the compilation of the words.hk Cantonese dictionary dataset, which was compiled through manual annotation over a period of 7 years. Cantonese is a low-resource language with limited tagged or manually checked resources, especially at the sentential level, and this dataset is an attempt to fill the gap. The dataset contains over 53,000 entries of Cantonese words, which comes with basic lexical information (Jyutping phonemic transcription, part-of-speech tags, usage tags), manually crafted definitions in Written Cantonese, English translations, and Cantonese examples with English translation and Jyutping transliterations. Special attention has been paid to handle character variants, so that unintended “character errors” (equivalent to typos in phonemic writing systems) are filtered out, and intra-speaker variants are handled. Fine details on word segmentation, character variant handling, definition crafting will be discussed. The dataset can be used in a wide range of natural language processing tasks, such as word segmentation, construction of semantic web and training of models for Cantonese transliteration.</abstract>
<identifier type="citekey">lau-etal-2022-words</identifier>
<location>
<url>https://aclanthology.org/2022.dclrl-1.7</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>53</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Words.hk: A Comprehensive Cantonese Dictionary Dataset with Definitions, Translations and Transliterated Examples
%A Lau, Chaak-ming
%A Chan, Grace Wing-yan
%A Tse, Raymond Ka-wai
%A Chan, Lilian Suet-ying
%Y Sälevä, Jonne
%Y Lignos, Constantine
%S Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F lau-etal-2022-words
%X This paper discusses the compilation of the words.hk Cantonese dictionary dataset, which was compiled through manual annotation over a period of 7 years. Cantonese is a low-resource language with limited tagged or manually checked resources, especially at the sentential level, and this dataset is an attempt to fill the gap. The dataset contains over 53,000 entries of Cantonese words, which comes with basic lexical information (Jyutping phonemic transcription, part-of-speech tags, usage tags), manually crafted definitions in Written Cantonese, English translations, and Cantonese examples with English translation and Jyutping transliterations. Special attention has been paid to handle character variants, so that unintended “character errors” (equivalent to typos in phonemic writing systems) are filtered out, and intra-speaker variants are handled. Fine details on word segmentation, character variant handling, definition crafting will be discussed. The dataset can be used in a wide range of natural language processing tasks, such as word segmentation, construction of semantic web and training of models for Cantonese transliteration.
%U https://aclanthology.org/2022.dclrl-1.7
%P 53-62
Markdown (Informal)
[Words.hk: A Comprehensive Cantonese Dictionary Dataset with Definitions, Translations and Transliterated Examples](https://aclanthology.org/2022.dclrl-1.7) (Lau et al., DCLRL 2022)
ACL