@inproceedings{zhou-etal-2023-wyweb,
title = "{WYWEB}: A {NLP} Evaluation Benchmark For Classical {C}hinese",
author = "Zhou, Bo and
Chen, Qianglong and
Wang, Tianyu and
Zhong, Xiaomi and
Zhang, Yin",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.204",
doi = "10.18653/v1/2023.findings-acl.204",
pages = "3294--3319",
abstract = "To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE. The field of natural language understanding has traditionally focused on benchmarks for various tasks in languages such as Chinese, English, and multilingual, however, there has been a lack of attention given to the area of classical Chinese, also known as ``wen yan wen (文言文)'', which has a rich history spanning thousands of years and holds significant cultural and academic value. For the prosperity of the NLP community, in this paper, we introduce the WYWEB evaluation benchmark, which consists of nine NLP tasks in classical Chinese, implementing sentence classification, sequence labeling, reading comprehension, and machine translation. We evaluate the existing pre-trained language models, which are all struggling with this benchmark. We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on classical Chinese NLU. The github repository is \url{https://github.com/baudzhou/WYWEB}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2023-wyweb">
<titleInfo>
<title>WYWEB: A NLP Evaluation Benchmark For Classical Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianglong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaomi</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE. The field of natural language understanding has traditionally focused on benchmarks for various tasks in languages such as Chinese, English, and multilingual, however, there has been a lack of attention given to the area of classical Chinese, also known as “wen yan wen (文言文)”, which has a rich history spanning thousands of years and holds significant cultural and academic value. For the prosperity of the NLP community, in this paper, we introduce the WYWEB evaluation benchmark, which consists of nine NLP tasks in classical Chinese, implementing sentence classification, sequence labeling, reading comprehension, and machine translation. We evaluate the existing pre-trained language models, which are all struggling with this benchmark. We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on classical Chinese NLU. The github repository is https://github.com/baudzhou/WYWEB.</abstract>
<identifier type="citekey">zhou-etal-2023-wyweb</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.204</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.204</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3294</start>
<end>3319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WYWEB: A NLP Evaluation Benchmark For Classical Chinese
%A Zhou, Bo
%A Chen, Qianglong
%A Wang, Tianyu
%A Zhong, Xiaomi
%A Zhang, Yin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhou-etal-2023-wyweb
%X To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE. The field of natural language understanding has traditionally focused on benchmarks for various tasks in languages such as Chinese, English, and multilingual, however, there has been a lack of attention given to the area of classical Chinese, also known as “wen yan wen (文言文)”, which has a rich history spanning thousands of years and holds significant cultural and academic value. For the prosperity of the NLP community, in this paper, we introduce the WYWEB evaluation benchmark, which consists of nine NLP tasks in classical Chinese, implementing sentence classification, sequence labeling, reading comprehension, and machine translation. We evaluate the existing pre-trained language models, which are all struggling with this benchmark. We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on classical Chinese NLU. The github repository is https://github.com/baudzhou/WYWEB.
%R 10.18653/v1/2023.findings-acl.204
%U https://aclanthology.org/2023.findings-acl.204
%U https://doi.org/10.18653/v1/2023.findings-acl.204
%P 3294-3319
Markdown (Informal)
[WYWEB: A NLP Evaluation Benchmark For Classical Chinese](https://aclanthology.org/2023.findings-acl.204) (Zhou et al., Findings 2023)
ACL
- Bo Zhou, Qianglong Chen, Tianyu Wang, Xiaomi Zhong, and Yin Zhang. 2023. WYWEB: A NLP Evaluation Benchmark For Classical Chinese. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3294–3319, Toronto, Canada. Association for Computational Linguistics.