@inproceedings{mino-etal-2021-nhks,
title = "{NHK}{'}s Lexically-Constrained Neural Machine Translation at {WAT} 2021",
author = "Mino, Hideya and
Kinugawa, Kazutaka and
Ito, Hitoshi and
Goto, Isao and
Yamada, Ichiro and
Tokunaga, Takenobu",
booktitle = "Proceedings of the 8th Workshop on Asian Translation (WAT2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wat-1.2",
doi = "10.18653/v1/2021.wat-1.2",
pages = "46--52",
abstract = "This paper describes the system of our team (NHK) for the WAT 2021 Japanese-English restricted machine translation task. In this task, the aim is to improve quality while maintaining consistent terminology for scientific paper translation. This task has a unique feature, where some words in a target sentence are given in addition to a source sentence. In this paper, we use a lexically-constrained neural machine translation (NMT), which concatenates the source sentence and constrained words with a special token to input them into the encoder of NMT. The key to the successful lexically-constrained NMT is the way to extract constraints from a target sentence of training data. We propose two extraction methods: proper-noun constraint and mistranslated-word constraint. These two methods consider the importance of words and fallibility of NMT, respectively. The evaluation results demonstrate the effectiveness of our lexical-constraint method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mino-etal-2021-nhks">
<titleInfo>
<title>NHK’s Lexically-Constrained Neural Machine Translation at WAT 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hideya</namePart>
<namePart type="family">Mino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazutaka</namePart>
<namePart type="family">Kinugawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Ito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ichiro</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takenobu</namePart>
<namePart type="family">Tokunaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Asian Translation (WAT2021)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system of our team (NHK) for the WAT 2021 Japanese-English restricted machine translation task. In this task, the aim is to improve quality while maintaining consistent terminology for scientific paper translation. This task has a unique feature, where some words in a target sentence are given in addition to a source sentence. In this paper, we use a lexically-constrained neural machine translation (NMT), which concatenates the source sentence and constrained words with a special token to input them into the encoder of NMT. The key to the successful lexically-constrained NMT is the way to extract constraints from a target sentence of training data. We propose two extraction methods: proper-noun constraint and mistranslated-word constraint. These two methods consider the importance of words and fallibility of NMT, respectively. The evaluation results demonstrate the effectiveness of our lexical-constraint method.</abstract>
<identifier type="citekey">mino-etal-2021-nhks</identifier>
<identifier type="doi">10.18653/v1/2021.wat-1.2</identifier>
<location>
<url>https://aclanthology.org/2021.wat-1.2</url>
</location>
<part>
<date>2021-aug</date>
<extent unit="page">
<start>46</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NHK’s Lexically-Constrained Neural Machine Translation at WAT 2021
%A Mino, Hideya
%A Kinugawa, Kazutaka
%A Ito, Hitoshi
%A Goto, Isao
%A Yamada, Ichiro
%A Tokunaga, Takenobu
%S Proceedings of the 8th Workshop on Asian Translation (WAT2021)
%D 2021
%8 aug
%I Association for Computational Linguistics
%C Online
%F mino-etal-2021-nhks
%X This paper describes the system of our team (NHK) for the WAT 2021 Japanese-English restricted machine translation task. In this task, the aim is to improve quality while maintaining consistent terminology for scientific paper translation. This task has a unique feature, where some words in a target sentence are given in addition to a source sentence. In this paper, we use a lexically-constrained neural machine translation (NMT), which concatenates the source sentence and constrained words with a special token to input them into the encoder of NMT. The key to the successful lexically-constrained NMT is the way to extract constraints from a target sentence of training data. We propose two extraction methods: proper-noun constraint and mistranslated-word constraint. These two methods consider the importance of words and fallibility of NMT, respectively. The evaluation results demonstrate the effectiveness of our lexical-constraint method.
%R 10.18653/v1/2021.wat-1.2
%U https://aclanthology.org/2021.wat-1.2
%U https://doi.org/10.18653/v1/2021.wat-1.2
%P 46-52
Markdown (Informal)
[NHK’s Lexically-Constrained Neural Machine Translation at WAT 2021](https://aclanthology.org/2021.wat-1.2) (Mino et al., WAT 2021)
ACL