@inproceedings{kessler-2024-towards,
title = "Towards Context-aware Normalization of Variant Characters in Classical {C}hinese Using Parallel Editions and {BERT}",
author = "Kessler, Florian",
editor = "Pavlopoulos, John and
Sommerschield, Thea and
Assael, Yannis and
Gordin, Shai and
Cho, Kyunghyun and
Passarotti, Marco and
Sprugnoli, Rachele and
Liu, Yudong and
Li, Bin and
Anderson, Adam",
booktitle = "Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)",
month = aug,
year = "2024",
address = "Hybrid in Bangkok, Thailand and online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ml4al-1.15",
pages = "141--151",
abstract = "For the automatic processing of Classical Chinese texts it is highly desirable to normalize variant characters, i.e. characters with different visual forms that are being used to represent the same morpheme, into a single form. However, there are some variant characters that are used interchangeably by some writers but deliberately employed to distinguish between different meanings by others. Hence, in order to avoid losing information in the normalization processes by conflating meaningful distinctions between variants, an intelligent normalization system that takes context into account is needed. Towards the goal of developing such a system, in this study, we describe how a dataset with usage samples of variant characters can be extracted from a corpus of paired editions of multiple texts. Using the dataset, we conduct two experiments, testing whether models can be trained with contextual word embeddings to predict variant characters. The results of the experiments show that while this is often possible for single texts, most conventions learned do not transfer well between documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kessler-2024-towards">
<titleInfo>
<title>Towards Context-aware Normalization of Variant Characters in Classical Chinese Using Parallel Editions and BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Kessler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thea</namePart>
<namePart type="family">Sommerschield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannis</namePart>
<namePart type="family">Assael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</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>
<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">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid in Bangkok, Thailand and online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For the automatic processing of Classical Chinese texts it is highly desirable to normalize variant characters, i.e. characters with different visual forms that are being used to represent the same morpheme, into a single form. However, there are some variant characters that are used interchangeably by some writers but deliberately employed to distinguish between different meanings by others. Hence, in order to avoid losing information in the normalization processes by conflating meaningful distinctions between variants, an intelligent normalization system that takes context into account is needed. Towards the goal of developing such a system, in this study, we describe how a dataset with usage samples of variant characters can be extracted from a corpus of paired editions of multiple texts. Using the dataset, we conduct two experiments, testing whether models can be trained with contextual word embeddings to predict variant characters. The results of the experiments show that while this is often possible for single texts, most conventions learned do not transfer well between documents.</abstract>
<identifier type="citekey">kessler-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.ml4al-1.15</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>141</start>
<end>151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Context-aware Normalization of Variant Characters in Classical Chinese Using Parallel Editions and BERT
%A Kessler, Florian
%Y Pavlopoulos, John
%Y Sommerschield, Thea
%Y Assael, Yannis
%Y Gordin, Shai
%Y Cho, Kyunghyun
%Y Passarotti, Marco
%Y Sprugnoli, Rachele
%Y Liu, Yudong
%Y Li, Bin
%Y Anderson, Adam
%S Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Hybrid in Bangkok, Thailand and online
%F kessler-2024-towards
%X For the automatic processing of Classical Chinese texts it is highly desirable to normalize variant characters, i.e. characters with different visual forms that are being used to represent the same morpheme, into a single form. However, there are some variant characters that are used interchangeably by some writers but deliberately employed to distinguish between different meanings by others. Hence, in order to avoid losing information in the normalization processes by conflating meaningful distinctions between variants, an intelligent normalization system that takes context into account is needed. Towards the goal of developing such a system, in this study, we describe how a dataset with usage samples of variant characters can be extracted from a corpus of paired editions of multiple texts. Using the dataset, we conduct two experiments, testing whether models can be trained with contextual word embeddings to predict variant characters. The results of the experiments show that while this is often possible for single texts, most conventions learned do not transfer well between documents.
%U https://aclanthology.org/2024.ml4al-1.15
%P 141-151
Markdown (Informal)
[Towards Context-aware Normalization of Variant Characters in Classical Chinese Using Parallel Editions and BERT](https://aclanthology.org/2024.ml4al-1.15) (Kessler, ML4AL-WS 2024)
ACL