@inproceedings{lau-etal-2024-extraction,
title = "The Extraction and Fine-grained Classification of Written {C}antonese Materials through Linguistic Feature Detection",
author = "Lau, Chaak-ming and
Lau, Mingfei and
To, Ann Wai Huen",
editor = "Ojha, Atul Kr. and
Ahmadi, Sina and
Cinkov{\'a}, Silvie and
Fransen, Theodorus and
Liu, Chao-Hong and
McCrae, John P.",
booktitle = "Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.eurali-1.4",
pages = "24--29",
abstract = "This paper presents a linguistically-informed, non-machine-learning tool for classifying Written Cantonese, Standard Written Chinese, and the intermediate varieties used by Cantonese-speaking users from Hong Kong, which are often grouped into a single {``}Traditional Chinese{''} label. Our approach addresses the lack of textual materials for Cantonese NLP, a consequence of a lower sociolinguistic status of Written Cantonese and the interchangeable use of these varieties by users without sufficient language labeling. The tool utilizes key strings and quotation markers, which can be reduced to string operations, to effectively extract Written Cantonese sentences and documents from materials mixed with Standard Written Chinese. This allows for the flexible and efficient extraction of high-quality Cantonese data from large datasets, catering to specific classification needs. This implementation ensures that the tool can process large amounts of data at a low cost by bypassing model-inferencing, which is particularly significant for marginalized languages. The tool also aims to provide a baseline measure for future classification systems, and the approach may be applicable to other low-resource regional or diglossic languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lau-etal-2024-extraction">
<titleInfo>
<title>The Extraction and Fine-grained Classification of Written Cantonese Materials through Linguistic Feature Detection</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">Mingfei</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="given">Wai</namePart>
<namePart type="given">Huen</namePart>
<namePart type="family">To</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvie</namePart>
<namePart type="family">Cinková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodorus</namePart>
<namePart type="family">Fransen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a linguistically-informed, non-machine-learning tool for classifying Written Cantonese, Standard Written Chinese, and the intermediate varieties used by Cantonese-speaking users from Hong Kong, which are often grouped into a single “Traditional Chinese” label. Our approach addresses the lack of textual materials for Cantonese NLP, a consequence of a lower sociolinguistic status of Written Cantonese and the interchangeable use of these varieties by users without sufficient language labeling. The tool utilizes key strings and quotation markers, which can be reduced to string operations, to effectively extract Written Cantonese sentences and documents from materials mixed with Standard Written Chinese. This allows for the flexible and efficient extraction of high-quality Cantonese data from large datasets, catering to specific classification needs. This implementation ensures that the tool can process large amounts of data at a low cost by bypassing model-inferencing, which is particularly significant for marginalized languages. The tool also aims to provide a baseline measure for future classification systems, and the approach may be applicable to other low-resource regional or diglossic languages.</abstract>
<identifier type="citekey">lau-etal-2024-extraction</identifier>
<location>
<url>https://aclanthology.org/2024.eurali-1.4</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>24</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Extraction and Fine-grained Classification of Written Cantonese Materials through Linguistic Feature Detection
%A Lau, Chaak-ming
%A Lau, Mingfei
%A To, Ann Wai Huen
%Y Ojha, Atul Kr.
%Y Ahmadi, Sina
%Y Cinková, Silvie
%Y Fransen, Theodorus
%Y Liu, Chao-Hong
%Y McCrae, John P.
%S Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lau-etal-2024-extraction
%X This paper presents a linguistically-informed, non-machine-learning tool for classifying Written Cantonese, Standard Written Chinese, and the intermediate varieties used by Cantonese-speaking users from Hong Kong, which are often grouped into a single “Traditional Chinese” label. Our approach addresses the lack of textual materials for Cantonese NLP, a consequence of a lower sociolinguistic status of Written Cantonese and the interchangeable use of these varieties by users without sufficient language labeling. The tool utilizes key strings and quotation markers, which can be reduced to string operations, to effectively extract Written Cantonese sentences and documents from materials mixed with Standard Written Chinese. This allows for the flexible and efficient extraction of high-quality Cantonese data from large datasets, catering to specific classification needs. This implementation ensures that the tool can process large amounts of data at a low cost by bypassing model-inferencing, which is particularly significant for marginalized languages. The tool also aims to provide a baseline measure for future classification systems, and the approach may be applicable to other low-resource regional or diglossic languages.
%U https://aclanthology.org/2024.eurali-1.4
%P 24-29
Markdown (Informal)
[The Extraction and Fine-grained Classification of Written Cantonese Materials through Linguistic Feature Detection](https://aclanthology.org/2024.eurali-1.4) (Lau et al., EURALI-WS 2024)
ACL