@inproceedings{li-etal-2022-first,
title = "The First International {A}ncient {C}hinese Word Segmentation and {POS} Tagging Bakeoff: Overview of the {E}va{H}an 2022 Evaluation Campaign",
author = "Li, Bin and
Yuan, Yiguo and
Lu, Jingya and
Feng, Minxuan and
Xu, Chao and
Qu, Weiguang and
Wang, Dongbo",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lt4hala-1.19",
pages = "135--140",
abstract = "This paper presents the results of the First Ancient Chinese Word Segmentation and POS Tagging Bakeoff (EvaHan), which was held at the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) 2022, in the context of the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022). We give the motivation for having an international shared contest, as well as the data and tracks. The contest is consisted of two modalities, closed and open. In the closed modality, the participants are only allowed to use the training data, obtained the highest F1 score of 96.03{\%} and 92.05{\%} in word segmentation and POS tagging. In the open modality, the participants can use whatever resource they have, with the highest F1 score of 96.34{\%} and 92.56{\%} in word segmentation and POS tagging. The scores on the blind test dataset decrease around 3 points, which shows that the out-of-vocabulary words still are the bottleneck for lexical analyzers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-first">
<titleInfo>
<title>The First International Ancient Chinese Word Segmentation and POS Tagging Bakeoff: Overview of the EvaHan 2022 Evaluation Campaign</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiguo</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingya</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minxuan</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiguang</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongbo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the results of the First Ancient Chinese Word Segmentation and POS Tagging Bakeoff (EvaHan), which was held at the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) 2022, in the context of the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022). We give the motivation for having an international shared contest, as well as the data and tracks. The contest is consisted of two modalities, closed and open. In the closed modality, the participants are only allowed to use the training data, obtained the highest F1 score of 96.03% and 92.05% in word segmentation and POS tagging. In the open modality, the participants can use whatever resource they have, with the highest F1 score of 96.34% and 92.56% in word segmentation and POS tagging. The scores on the blind test dataset decrease around 3 points, which shows that the out-of-vocabulary words still are the bottleneck for lexical analyzers.</abstract>
<identifier type="citekey">li-etal-2022-first</identifier>
<location>
<url>https://aclanthology.org/2022.lt4hala-1.19</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>135</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The First International Ancient Chinese Word Segmentation and POS Tagging Bakeoff: Overview of the EvaHan 2022 Evaluation Campaign
%A Li, Bin
%A Yuan, Yiguo
%A Lu, Jingya
%A Feng, Minxuan
%A Xu, Chao
%A Qu, Weiguang
%A Wang, Dongbo
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F li-etal-2022-first
%X This paper presents the results of the First Ancient Chinese Word Segmentation and POS Tagging Bakeoff (EvaHan), which was held at the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) 2022, in the context of the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022). We give the motivation for having an international shared contest, as well as the data and tracks. The contest is consisted of two modalities, closed and open. In the closed modality, the participants are only allowed to use the training data, obtained the highest F1 score of 96.03% and 92.05% in word segmentation and POS tagging. In the open modality, the participants can use whatever resource they have, with the highest F1 score of 96.34% and 92.56% in word segmentation and POS tagging. The scores on the blind test dataset decrease around 3 points, which shows that the out-of-vocabulary words still are the bottleneck for lexical analyzers.
%U https://aclanthology.org/2022.lt4hala-1.19
%P 135-140
Markdown (Informal)
[The First International Ancient Chinese Word Segmentation and POS Tagging Bakeoff: Overview of the EvaHan 2022 Evaluation Campaign](https://aclanthology.org/2022.lt4hala-1.19) (Li et al., LT4HALA 2022)
ACL