@inproceedings{pan-etal-2022-zuo,
title = "Zuo Zhuan {A}ncient {C}hinese Dataset for Word Sense Disambiguation",
author = "Pan, Xiaomeng and
Wang, Hongfei and
Oka, Teruaki and
Komachi, Mamoru",
editor = "Ippolito, Daphne and
Li, Liunian Harold and
Pacheco, Maria Leonor and
Chen, Danqi and
Xue, Nianwen",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-srw.17/",
doi = "10.18653/v1/2022.naacl-srw.17",
pages = "129--135",
abstract = "Word Sense Disambiguation (WSD) is a core task in Natural Language Processing (NLP). Ancient Chinese has rarely been used in WSD tasks, however, as no public dataset for ancient Chinese WSD tasks exists. Creation of an ancient Chinese dataset is considered a significant challenge because determining the most appropriate sense in a context is difficult and time-consuming owing to the different usages in ancient and modern Chinese. Actually, no public dataset for ancient Chinese WSD tasks exists. To solve the problem of ancient Chinese WSD, we annotate part of Pre-Qin (221 BC) text \textit{Zuo Zhuan} using a copyright-free dictionary to create a public sense-tagged dataset. Then, we apply a simple Nearest Neighbors (k-NN) method using a pre-trained language model to the dataset. Our code and dataset will be available on GitHub."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-etal-2022-zuo">
<titleInfo>
<title>Zuo Zhuan Ancient Chinese Dataset for Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaomeng</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teruaki</namePart>
<namePart type="family">Oka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daphne</namePart>
<namePart type="family">Ippolito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liunian</namePart>
<namePart type="given">Harold</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Leonor</namePart>
<namePart type="family">Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</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>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Sense Disambiguation (WSD) is a core task in Natural Language Processing (NLP). Ancient Chinese has rarely been used in WSD tasks, however, as no public dataset for ancient Chinese WSD tasks exists. Creation of an ancient Chinese dataset is considered a significant challenge because determining the most appropriate sense in a context is difficult and time-consuming owing to the different usages in ancient and modern Chinese. Actually, no public dataset for ancient Chinese WSD tasks exists. To solve the problem of ancient Chinese WSD, we annotate part of Pre-Qin (221 BC) text Zuo Zhuan using a copyright-free dictionary to create a public sense-tagged dataset. Then, we apply a simple Nearest Neighbors (k-NN) method using a pre-trained language model to the dataset. Our code and dataset will be available on GitHub.</abstract>
<identifier type="citekey">pan-etal-2022-zuo</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-srw.17</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-srw.17/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>129</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zuo Zhuan Ancient Chinese Dataset for Word Sense Disambiguation
%A Pan, Xiaomeng
%A Wang, Hongfei
%A Oka, Teruaki
%A Komachi, Mamoru
%Y Ippolito, Daphne
%Y Li, Liunian Harold
%Y Pacheco, Maria Leonor
%Y Chen, Danqi
%Y Xue, Nianwen
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F pan-etal-2022-zuo
%X Word Sense Disambiguation (WSD) is a core task in Natural Language Processing (NLP). Ancient Chinese has rarely been used in WSD tasks, however, as no public dataset for ancient Chinese WSD tasks exists. Creation of an ancient Chinese dataset is considered a significant challenge because determining the most appropriate sense in a context is difficult and time-consuming owing to the different usages in ancient and modern Chinese. Actually, no public dataset for ancient Chinese WSD tasks exists. To solve the problem of ancient Chinese WSD, we annotate part of Pre-Qin (221 BC) text Zuo Zhuan using a copyright-free dictionary to create a public sense-tagged dataset. Then, we apply a simple Nearest Neighbors (k-NN) method using a pre-trained language model to the dataset. Our code and dataset will be available on GitHub.
%R 10.18653/v1/2022.naacl-srw.17
%U https://aclanthology.org/2022.naacl-srw.17/
%U https://doi.org/10.18653/v1/2022.naacl-srw.17
%P 129-135
Markdown (Informal)
[Zuo Zhuan Ancient Chinese Dataset for Word Sense Disambiguation](https://aclanthology.org/2022.naacl-srw.17/) (Pan et al., NAACL 2022)
ACL
- Xiaomeng Pan, Hongfei Wang, Teruaki Oka, and Mamoru Komachi. 2022. Zuo Zhuan Ancient Chinese Dataset for Word Sense Disambiguation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pages 129–135, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.