@inproceedings{chang-etal-2022-wikihan,
title = "{W}iki{H}an: A New Comparative Dataset for {C}hinese Languages",
author = "Chang, Kalvin and
Cui, Chenxuan and
Kim, Youngmin and
Mortensen, David R.",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.314",
pages = "3563--3569",
abstract = "Most comparative datasets of Chinese varieties are not digital; however, Wiktionary includes a wealth of transcriptions of words from these varieties. The usefulness of these data is limited by the fact that they use a wide range of variety-specific romanizations, making data difficult to compare. The current work collects this data into a single constituent (IPA, or International Phonetic Alphabet) and structured form (TSV) for use in comparative linguistics and Chinese NLP. At the time of writing, the dataset contains 67,943 entries across 8 varieties and Middle Chinese. The dataset is validated on a protoform reconstruction task using an encoder-decoder cross-attention architecture (Meloni et al 2021), achieving an accuracy of 54.11{\%}, a PER (phoneme error rate) of 17.69{\%}, and a FER (feature error rate) of 6.60{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2022-wikihan">
<titleInfo>
<title>WikiHan: A New Comparative Dataset for Chinese Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalvin</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxuan</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngmin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Mortensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most comparative datasets of Chinese varieties are not digital; however, Wiktionary includes a wealth of transcriptions of words from these varieties. The usefulness of these data is limited by the fact that they use a wide range of variety-specific romanizations, making data difficult to compare. The current work collects this data into a single constituent (IPA, or International Phonetic Alphabet) and structured form (TSV) for use in comparative linguistics and Chinese NLP. At the time of writing, the dataset contains 67,943 entries across 8 varieties and Middle Chinese. The dataset is validated on a protoform reconstruction task using an encoder-decoder cross-attention architecture (Meloni et al 2021), achieving an accuracy of 54.11%, a PER (phoneme error rate) of 17.69%, and a FER (feature error rate) of 6.60%.</abstract>
<identifier type="citekey">chang-etal-2022-wikihan</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.314</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3563</start>
<end>3569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiHan: A New Comparative Dataset for Chinese Languages
%A Chang, Kalvin
%A Cui, Chenxuan
%A Kim, Youngmin
%A Mortensen, David R.
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F chang-etal-2022-wikihan
%X Most comparative datasets of Chinese varieties are not digital; however, Wiktionary includes a wealth of transcriptions of words from these varieties. The usefulness of these data is limited by the fact that they use a wide range of variety-specific romanizations, making data difficult to compare. The current work collects this data into a single constituent (IPA, or International Phonetic Alphabet) and structured form (TSV) for use in comparative linguistics and Chinese NLP. At the time of writing, the dataset contains 67,943 entries across 8 varieties and Middle Chinese. The dataset is validated on a protoform reconstruction task using an encoder-decoder cross-attention architecture (Meloni et al 2021), achieving an accuracy of 54.11%, a PER (phoneme error rate) of 17.69%, and a FER (feature error rate) of 6.60%.
%U https://aclanthology.org/2022.coling-1.314
%P 3563-3569
Markdown (Informal)
[WikiHan: A New Comparative Dataset for Chinese Languages](https://aclanthology.org/2022.coling-1.314) (Chang et al., COLING 2022)
ACL
- Kalvin Chang, Chenxuan Cui, Youngmin Kim, and David R. Mortensen. 2022. WikiHan: A New Comparative Dataset for Chinese Languages. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3563–3569, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.