@inproceedings{dai-yamaguchi-2019-compact,
title = "Compact and Robust Models for {J}apanese-{E}nglish Character-level Machine Translation",
author = "Dai, Jinan and
Yamaguchi, Kazunori",
booktitle = "Proceedings of the 6th Workshop on Asian Translation",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5202",
doi = "10.18653/v1/D19-5202",
pages = "36--44",
abstract = "Character-level translation has been proved to be able to achieve preferable translation quality without explicit segmentation, but training a character-level model needs a lot of hardware resources. In this paper, we introduced two character-level translation models which are mid-gated model and multi-attention model for Japanese-English translation. We showed that the mid-gated model achieved the better performance with respect to BLEU scores. We also showed that a relatively narrow beam of width 4 or 5 was sufficient for the mid-gated model. As for unknown words, we showed that the mid-gated model could somehow translate the one containing Katakana by coining out a close word. We also showed that the model managed to produce tolerable results for heavily noised sentences, even though the model was trained with the dataset without noise.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dai-yamaguchi-2019-compact">
<titleInfo>
<title>Compact and Robust Models for Japanese-English Character-level Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Asian Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Character-level translation has been proved to be able to achieve preferable translation quality without explicit segmentation, but training a character-level model needs a lot of hardware resources. In this paper, we introduced two character-level translation models which are mid-gated model and multi-attention model for Japanese-English translation. We showed that the mid-gated model achieved the better performance with respect to BLEU scores. We also showed that a relatively narrow beam of width 4 or 5 was sufficient for the mid-gated model. As for unknown words, we showed that the mid-gated model could somehow translate the one containing Katakana by coining out a close word. We also showed that the model managed to produce tolerable results for heavily noised sentences, even though the model was trained with the dataset without noise.</abstract>
<identifier type="citekey">dai-yamaguchi-2019-compact</identifier>
<identifier type="doi">10.18653/v1/D19-5202</identifier>
<location>
<url>https://aclanthology.org/D19-5202</url>
</location>
<part>
<date>2019-nov</date>
<extent unit="page">
<start>36</start>
<end>44</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Compact and Robust Models for Japanese-English Character-level Machine Translation
%A Dai, Jinan
%A Yamaguchi, Kazunori
%S Proceedings of the 6th Workshop on Asian Translation
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong, China
%F dai-yamaguchi-2019-compact
%X Character-level translation has been proved to be able to achieve preferable translation quality without explicit segmentation, but training a character-level model needs a lot of hardware resources. In this paper, we introduced two character-level translation models which are mid-gated model and multi-attention model for Japanese-English translation. We showed that the mid-gated model achieved the better performance with respect to BLEU scores. We also showed that a relatively narrow beam of width 4 or 5 was sufficient for the mid-gated model. As for unknown words, we showed that the mid-gated model could somehow translate the one containing Katakana by coining out a close word. We also showed that the model managed to produce tolerable results for heavily noised sentences, even though the model was trained with the dataset without noise.
%R 10.18653/v1/D19-5202
%U https://aclanthology.org/D19-5202
%U https://doi.org/10.18653/v1/D19-5202
%P 36-44
Markdown (Informal)
[Compact and Robust Models for Japanese-English Character-level Machine Translation](https://aclanthology.org/D19-5202) (Dai & Yamaguchi, EMNLP 2019)
ACL