@inproceedings{wong-etal-2024-humanistic,
title = "Humanistic Buddhism Corpus: A Challenging Domain-Specific Dataset of {E}nglish Translations for Classical and {M}odern {C}hinese",
author = "Wong, Youheng W. and
Parde, Natalie and
Koyuncu, Erdem",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.737/",
pages = "8406--8417",
abstract = "We introduce the Humanistic Buddhism Corpus (HBC), a dataset containing over 80,000 Chinese-English parallel phrases extracted and translated from publications in the domain of Buddhism. HBC is one of the largest free domain-specific datasets that is publicly available for research, containing text from both classical and modern Chinese. Moreover, since HBC originates from religious texts, many phrases in the dataset contain metaphors and symbolism, and are subject to multiple interpretations. Compared to existing machine translation datasets, HBC presents difficult unique challenges. In this paper, we describe HBC in detail. We evaluate HBC within a machine translation setting, validating its use by establishing performance benchmarks using a Transformer model with different transfer learning setups."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wong-etal-2024-humanistic">
<titleInfo>
<title>Humanistic Buddhism Corpus: A Challenging Domain-Specific Dataset of English Translations for Classical and Modern Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Youheng</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erdem</namePart>
<namePart type="family">Koyuncu</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>We introduce the Humanistic Buddhism Corpus (HBC), a dataset containing over 80,000 Chinese-English parallel phrases extracted and translated from publications in the domain of Buddhism. HBC is one of the largest free domain-specific datasets that is publicly available for research, containing text from both classical and modern Chinese. Moreover, since HBC originates from religious texts, many phrases in the dataset contain metaphors and symbolism, and are subject to multiple interpretations. Compared to existing machine translation datasets, HBC presents difficult unique challenges. In this paper, we describe HBC in detail. We evaluate HBC within a machine translation setting, validating its use by establishing performance benchmarks using a Transformer model with different transfer learning setups.</abstract>
<identifier type="citekey">wong-etal-2024-humanistic</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.737/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8406</start>
<end>8417</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Humanistic Buddhism Corpus: A Challenging Domain-Specific Dataset of English Translations for Classical and Modern Chinese
%A Wong, Youheng W.
%A Parde, Natalie
%A Koyuncu, Erdem
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F wong-etal-2024-humanistic
%X We introduce the Humanistic Buddhism Corpus (HBC), a dataset containing over 80,000 Chinese-English parallel phrases extracted and translated from publications in the domain of Buddhism. HBC is one of the largest free domain-specific datasets that is publicly available for research, containing text from both classical and modern Chinese. Moreover, since HBC originates from religious texts, many phrases in the dataset contain metaphors and symbolism, and are subject to multiple interpretations. Compared to existing machine translation datasets, HBC presents difficult unique challenges. In this paper, we describe HBC in detail. We evaluate HBC within a machine translation setting, validating its use by establishing performance benchmarks using a Transformer model with different transfer learning setups.
%U https://aclanthology.org/2024.lrec-main.737/
%P 8406-8417
Markdown (Informal)
[Humanistic Buddhism Corpus: A Challenging Domain-Specific Dataset of English Translations for Classical and Modern Chinese](https://aclanthology.org/2024.lrec-main.737/) (Wong et al., LREC-COLING 2024)
ACL