@inproceedings{usui-komiya-2023-translation,
title = "Translation from Historical to Contemporary {J}apanese Using {J}apanese T5",
author = "Usui, Hisao and
Komiya, Kanako",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Pirinen, Flammie and
Alnajjar, Khalid and
Miyagawa, So and
Bizzoni, Yuri and
Partanen, Niko and
Rueter, Jack},
booktitle = "Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages",
month = dec,
year = "2023",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nlp4dh-1.4",
pages = "27--35",
abstract = "This paper presents machine translation from historical Japanese to contemporary Japanese using a Text-to-Text Transfer Transformer (T5). The result of the previous study that used neural machine translation (NMT), Long Short Term Memory (LSTM), could not outperform that of the work that used statistical machine translation (SMT). Because an NMT model tends to require more training data than an SMT model, the lack of parallel data of historical and contemporary Japanese could be the reason. Therefore, we used Japanese T5, a kind of large language model to compensate for the lack of data. Our experiments show that the translation with T5 is slightly lower than SMT. In addition, we added the title of the literature book from which the example sentence was extracted at the beginning of the input. Japanese historical corpus consists of a variety of texts ranging in periods when the texts were written and the writing styles. Therefore, we expected that the title gives information about the period and style, to the translation model. Additional experiments revealed that, with title information, the translation from historical Japanese to contemporary Japanese with T5 surpassed that with SMT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="usui-komiya-2023-translation">
<titleInfo>
<title>Translation from Historical to Contemporary Japanese Using Japanese T5</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hisao</namePart>
<namePart type="family">Usui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanako</namePart>
<namePart type="family">Komiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents machine translation from historical Japanese to contemporary Japanese using a Text-to-Text Transfer Transformer (T5). The result of the previous study that used neural machine translation (NMT), Long Short Term Memory (LSTM), could not outperform that of the work that used statistical machine translation (SMT). Because an NMT model tends to require more training data than an SMT model, the lack of parallel data of historical and contemporary Japanese could be the reason. Therefore, we used Japanese T5, a kind of large language model to compensate for the lack of data. Our experiments show that the translation with T5 is slightly lower than SMT. In addition, we added the title of the literature book from which the example sentence was extracted at the beginning of the input. Japanese historical corpus consists of a variety of texts ranging in periods when the texts were written and the writing styles. Therefore, we expected that the title gives information about the period and style, to the translation model. Additional experiments revealed that, with title information, the translation from historical Japanese to contemporary Japanese with T5 surpassed that with SMT.</abstract>
<identifier type="citekey">usui-komiya-2023-translation</identifier>
<location>
<url>https://aclanthology.org/2023.nlp4dh-1.4</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>27</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation from Historical to Contemporary Japanese Using Japanese T5
%A Usui, Hisao
%A Komiya, Kanako
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Pirinen, Flammie
%Y Alnajjar, Khalid
%Y Miyagawa, So
%Y Bizzoni, Yuri
%Y Partanen, Niko
%Y Rueter, Jack
%S Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages
%D 2023
%8 December
%I Association for Computational Linguistics
%C Tokyo, Japan
%F usui-komiya-2023-translation
%X This paper presents machine translation from historical Japanese to contemporary Japanese using a Text-to-Text Transfer Transformer (T5). The result of the previous study that used neural machine translation (NMT), Long Short Term Memory (LSTM), could not outperform that of the work that used statistical machine translation (SMT). Because an NMT model tends to require more training data than an SMT model, the lack of parallel data of historical and contemporary Japanese could be the reason. Therefore, we used Japanese T5, a kind of large language model to compensate for the lack of data. Our experiments show that the translation with T5 is slightly lower than SMT. In addition, we added the title of the literature book from which the example sentence was extracted at the beginning of the input. Japanese historical corpus consists of a variety of texts ranging in periods when the texts were written and the writing styles. Therefore, we expected that the title gives information about the period and style, to the translation model. Additional experiments revealed that, with title information, the translation from historical Japanese to contemporary Japanese with T5 surpassed that with SMT.
%U https://aclanthology.org/2023.nlp4dh-1.4
%P 27-35
Markdown (Informal)
[Translation from Historical to Contemporary Japanese Using Japanese T5](https://aclanthology.org/2023.nlp4dh-1.4) (Usui & Komiya, NLP4DH-IWCLUL 2023)
ACL
- Hisao Usui and Kanako Komiya. 2023. Translation from Historical to Contemporary Japanese Using Japanese T5. In Proceedings of the Joint 3rd International Conference on Natural Language Processing for Digital Humanities and 8th International Workshop on Computational Linguistics for Uralic Languages, pages 27–35, Tokyo, Japan. Association for Computational Linguistics.