@inproceedings{poncelas-htun-2022-controlling,
title = "Controlling {J}apanese Machine Translation Output by Using {JLPT} Vocabulary Levels",
author = "Poncelas, Alberto and
Htun, Ohnmar",
editor = "{\v{S}}tajner, Sanja and
Saggion, Horacio and
Ferr{\'e}s, Daniel and
Shardlow, Matthew and
Sheang, Kim Cheng and
North, Kai and
Zampieri, Marcos and
Xu, Wei",
booktitle = "Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.tsar-1.7",
doi = "10.18653/v1/2022.tsar-1.7",
pages = "77--85",
abstract = "In Neural Machine Translation (NMT) systems, there is generally little control over the lexicon of the output. Consequently, the translated output may be too difficult for certain audiences. For example, for people with limited knowledge of the language, vocabulary is a major impediment to understanding a text. In this work, we build a complexity-controllable NMT for English-to-Japanese translations. More particularly, we aim to modulate the difficulty of the translation in terms of not only the vocabulary but also the use of kanji. For achieving this, we follow a sentence-tagging approach to influence the output. Controlling Japanese Machine Translation Output by Using JLPT Vocabulary Levels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poncelas-htun-2022-controlling">
<titleInfo>
<title>Controlling Japanese Machine Translation Output by Using JLPT Vocabulary Levels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Poncelas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ohnmar</namePart>
<namePart type="family">Htun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Štajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Ferrés</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="given">Cheng</namePart>
<namePart type="family">Sheang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In Neural Machine Translation (NMT) systems, there is generally little control over the lexicon of the output. Consequently, the translated output may be too difficult for certain audiences. For example, for people with limited knowledge of the language, vocabulary is a major impediment to understanding a text. In this work, we build a complexity-controllable NMT for English-to-Japanese translations. More particularly, we aim to modulate the difficulty of the translation in terms of not only the vocabulary but also the use of kanji. For achieving this, we follow a sentence-tagging approach to influence the output. Controlling Japanese Machine Translation Output by Using JLPT Vocabulary Levels.</abstract>
<identifier type="citekey">poncelas-htun-2022-controlling</identifier>
<identifier type="doi">10.18653/v1/2022.tsar-1.7</identifier>
<location>
<url>https://aclanthology.org/2022.tsar-1.7</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>77</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Controlling Japanese Machine Translation Output by Using JLPT Vocabulary Levels
%A Poncelas, Alberto
%A Htun, Ohnmar
%Y Štajner, Sanja
%Y Saggion, Horacio
%Y Ferrés, Daniel
%Y Shardlow, Matthew
%Y Sheang, Kim Cheng
%Y North, Kai
%Y Zampieri, Marcos
%Y Xu, Wei
%S Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Virtual)
%F poncelas-htun-2022-controlling
%X In Neural Machine Translation (NMT) systems, there is generally little control over the lexicon of the output. Consequently, the translated output may be too difficult for certain audiences. For example, for people with limited knowledge of the language, vocabulary is a major impediment to understanding a text. In this work, we build a complexity-controllable NMT for English-to-Japanese translations. More particularly, we aim to modulate the difficulty of the translation in terms of not only the vocabulary but also the use of kanji. For achieving this, we follow a sentence-tagging approach to influence the output. Controlling Japanese Machine Translation Output by Using JLPT Vocabulary Levels.
%R 10.18653/v1/2022.tsar-1.7
%U https://aclanthology.org/2022.tsar-1.7
%U https://doi.org/10.18653/v1/2022.tsar-1.7
%P 77-85
Markdown (Informal)
[Controlling Japanese Machine Translation Output by Using JLPT Vocabulary Levels](https://aclanthology.org/2022.tsar-1.7) (Poncelas & Htun, TSAR 2022)
ACL