@inproceedings{park-tsvetkov-2019-learning,
title = "Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation",
author = "Park, Chan Young and
Tsvetkov, Yulia",
editor = "Birch, Alexandra and
Finch, Andrew and
Hayashi, Hiroaki and
Konstas, Ioannis and
Luong, Thang and
Neubig, Graham and
Oda, Yusuke and
Sudoh, Katsuhito",
booktitle = "Proceedings of the 3rd Workshop on Neural Generation and Translation",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5626",
doi = "10.18653/v1/D19-5626",
pages = "241--248",
abstract = "Neural machine translation (NMT) often fails in one-to-many translation, e.g., in the translation of multi-word expressions, compounds, and collocations. To improve the translation of phrases, phrase-based NMT systems have been proposed; these typically combine word-based NMT with external phrase dictionaries or with phrase tables from phrase-based statistical MT systems. These solutions introduce a significant overhead of additional resources and computational costs. In this paper, we introduce a phrase-based NMT model built upon continuous-output NMT, in which the decoder generates embeddings of words or phrases. The model uses a fertility module, which guides the decoder to generate embeddings of sequences of varying lengths. We show that our model learns to translate phrases better, performing on par with state of the art phrase-based NMT. Since our model does not resort to softmax computation over a huge vocabulary of phrases, its training time is about 112x faster than the baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-tsvetkov-2019-learning">
<titleInfo>
<title>Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chan</namePart>
<namePart type="given">Young</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Neural Generation and Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thang</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural machine translation (NMT) often fails in one-to-many translation, e.g., in the translation of multi-word expressions, compounds, and collocations. To improve the translation of phrases, phrase-based NMT systems have been proposed; these typically combine word-based NMT with external phrase dictionaries or with phrase tables from phrase-based statistical MT systems. These solutions introduce a significant overhead of additional resources and computational costs. In this paper, we introduce a phrase-based NMT model built upon continuous-output NMT, in which the decoder generates embeddings of words or phrases. The model uses a fertility module, which guides the decoder to generate embeddings of sequences of varying lengths. We show that our model learns to translate phrases better, performing on par with state of the art phrase-based NMT. Since our model does not resort to softmax computation over a huge vocabulary of phrases, its training time is about 112x faster than the baseline.</abstract>
<identifier type="citekey">park-tsvetkov-2019-learning</identifier>
<identifier type="doi">10.18653/v1/D19-5626</identifier>
<location>
<url>https://aclanthology.org/D19-5626</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>241</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation
%A Park, Chan Young
%A Tsvetkov, Yulia
%Y Birch, Alexandra
%Y Finch, Andrew
%Y Hayashi, Hiroaki
%Y Konstas, Ioannis
%Y Luong, Thang
%Y Neubig, Graham
%Y Oda, Yusuke
%Y Sudoh, Katsuhito
%S Proceedings of the 3rd Workshop on Neural Generation and Translation
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F park-tsvetkov-2019-learning
%X Neural machine translation (NMT) often fails in one-to-many translation, e.g., in the translation of multi-word expressions, compounds, and collocations. To improve the translation of phrases, phrase-based NMT systems have been proposed; these typically combine word-based NMT with external phrase dictionaries or with phrase tables from phrase-based statistical MT systems. These solutions introduce a significant overhead of additional resources and computational costs. In this paper, we introduce a phrase-based NMT model built upon continuous-output NMT, in which the decoder generates embeddings of words or phrases. The model uses a fertility module, which guides the decoder to generate embeddings of sequences of varying lengths. We show that our model learns to translate phrases better, performing on par with state of the art phrase-based NMT. Since our model does not resort to softmax computation over a huge vocabulary of phrases, its training time is about 112x faster than the baseline.
%R 10.18653/v1/D19-5626
%U https://aclanthology.org/D19-5626
%U https://doi.org/10.18653/v1/D19-5626
%P 241-248
Markdown (Informal)
[Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation](https://aclanthology.org/D19-5626) (Park & Tsvetkov, NGT 2019)
ACL