@inproceedings{tian-guo-2022-ancient,
title = "{A}ncient {C}hinese Word Segmentation and Part-of-Speech Tagging Using Data Augmentation",
author = "Tian, Yanzhi and
Guo, Yuhang",
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-1.21",
pages = "146--149",
abstract = "We attended the EvaHan2022 ancient Chinese word segmentation and Part-of-Speech (POS) tagging evaluation. We regard the Chinese word segmentation and POS tagging as sequence tagging tasks. Our system is based on a BERT-BiLSTM-CRF model which is trained on the data provided by the EvaHan2022 evaluation. Besides, we also employ data augmentation techniques to enhance the performance of our model. On the Test A and Test B of the evaluation, the F1 scores of our system achieve 94.73{\%} and 90.93{\%} for the word segmentation, 89.19{\%} and 83.48{\%} for the POS tagging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-guo-2022-ancient">
<titleInfo>
<title>Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanzhi</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Guo</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>We attended the EvaHan2022 ancient Chinese word segmentation and Part-of-Speech (POS) tagging evaluation. We regard the Chinese word segmentation and POS tagging as sequence tagging tasks. Our system is based on a BERT-BiLSTM-CRF model which is trained on the data provided by the EvaHan2022 evaluation. Besides, we also employ data augmentation techniques to enhance the performance of our model. On the Test A and Test B of the evaluation, the F1 scores of our system achieve 94.73% and 90.93% for the word segmentation, 89.19% and 83.48% for the POS tagging.</abstract>
<identifier type="citekey">tian-guo-2022-ancient</identifier>
<location>
<url>https://aclanthology.org/2022.lt4hala-1.21</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>146</start>
<end>149</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Data Augmentation
%A Tian, Yanzhi
%A Guo, Yuhang
%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 tian-guo-2022-ancient
%X We attended the EvaHan2022 ancient Chinese word segmentation and Part-of-Speech (POS) tagging evaluation. We regard the Chinese word segmentation and POS tagging as sequence tagging tasks. Our system is based on a BERT-BiLSTM-CRF model which is trained on the data provided by the EvaHan2022 evaluation. Besides, we also employ data augmentation techniques to enhance the performance of our model. On the Test A and Test B of the evaluation, the F1 scores of our system achieve 94.73% and 90.93% for the word segmentation, 89.19% and 83.48% for the POS tagging.
%U https://aclanthology.org/2022.lt4hala-1.21
%P 146-149
Markdown (Informal)
[Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Data Augmentation](https://aclanthology.org/2022.lt4hala-1.21) (Tian & Guo, LT4HALA 2022)
ACL