@inproceedings{xinyuan-etal-2022-glyph,
title = "Glyph Features Matter: A Multimodal Solution for {E}va{H}an in {LT}4{HALA}2022",
author = "Xinyuan, Wei and
Weihao, Liu and
Zong, Qing and
Shaoqing, Zhang and
Hu, Baotian",
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-1.28",
pages = "178--182",
abstract = "We participate in the LT4HALA2022 shared task EvaHan. This task has two subtasks. Subtask 1 is word segmentation, and subtask 2 is part-of-speech tagging. Each subtask consists of two tracks, a close track that can only use the data and models provided by the organizer, and an open track without restrictions. We employ three pre-trained models, two of which are open-source pre-trained models for ancient Chinese (Siku-Roberta and roberta-classical-chinese), and one is our pre-trained GlyphBERT combined with glyph features. Our methods include data augmentation, data pre-processing, model pretraining, downstream fine-tuning, k-fold cross validation and model ensemble. We achieve competitive P, R, and F1 scores on both our own validation set and the final public test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xinyuan-etal-2022-glyph">
<titleInfo>
<title>Glyph Features Matter: A Multimodal Solution for EvaHan in LT4HALA2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xinyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Weihao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Shaoqing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baotian</namePart>
<namePart type="family">Hu</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 participate in the LT4HALA2022 shared task EvaHan. This task has two subtasks. Subtask 1 is word segmentation, and subtask 2 is part-of-speech tagging. Each subtask consists of two tracks, a close track that can only use the data and models provided by the organizer, and an open track without restrictions. We employ three pre-trained models, two of which are open-source pre-trained models for ancient Chinese (Siku-Roberta and roberta-classical-chinese), and one is our pre-trained GlyphBERT combined with glyph features. Our methods include data augmentation, data pre-processing, model pretraining, downstream fine-tuning, k-fold cross validation and model ensemble. We achieve competitive P, R, and F1 scores on both our own validation set and the final public test set.</abstract>
<identifier type="citekey">xinyuan-etal-2022-glyph</identifier>
<location>
<url>https://aclanthology.org/2022.lt4hala-1.28</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>178</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Glyph Features Matter: A Multimodal Solution for EvaHan in LT4HALA2022
%A Xinyuan, Wei
%A Weihao, Liu
%A Zong, Qing
%A Shaoqing, Zhang
%A Hu, Baotian
%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 xinyuan-etal-2022-glyph
%X We participate in the LT4HALA2022 shared task EvaHan. This task has two subtasks. Subtask 1 is word segmentation, and subtask 2 is part-of-speech tagging. Each subtask consists of two tracks, a close track that can only use the data and models provided by the organizer, and an open track without restrictions. We employ three pre-trained models, two of which are open-source pre-trained models for ancient Chinese (Siku-Roberta and roberta-classical-chinese), and one is our pre-trained GlyphBERT combined with glyph features. Our methods include data augmentation, data pre-processing, model pretraining, downstream fine-tuning, k-fold cross validation and model ensemble. We achieve competitive P, R, and F1 scores on both our own validation set and the final public test set.
%U https://aclanthology.org/2022.lt4hala-1.28
%P 178-182
Markdown (Informal)
[Glyph Features Matter: A Multimodal Solution for EvaHan in LT4HALA2022](https://aclanthology.org/2022.lt4hala-1.28) (Xinyuan et al., LT4HALA 2022)
ACL