@inproceedings{martinez-garcia-etal-2019-context,
title = "Context-Aware Neural Machine Translation Decoding",
author = "Mart{\'\i}nez Garcia, Eva and
Creus, Carles and
Espa{\~n}a-Bonet, Cristina",
editor = "Popescu-Belis, Andrei and
Lo{\'a}iciga, Sharid and
Hardmeier, Christian and
Xiong, Deyi",
booktitle = "Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6502",
doi = "10.18653/v1/D19-6502",
pages = "13--23",
abstract = "This work presents a decoding architecture that fuses the information from a neural translation model and the context semantics enclosed in a semantic space language model based on word embeddings. The method extends the beam search decoding process and therefore can be applied to any neural machine translation framework. With this, we sidestep two drawbacks of current document-level systems: (i) we do not modify the training process so there is no increment in training time, and (ii) we do not require document-level an-notated data. We analyze the impact of the fusion system approach and its parameters on the final translation quality for English{--}Spanish. We obtain consistent and statistically significant improvements in terms of BLEU and METEOR and we observe how the fused systems are able to handle synonyms to propose more adequate translations as well as help the system to disambiguate among several translation candidates for a word.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinez-garcia-etal-2019-context">
<titleInfo>
<title>Context-Aware Neural Machine Translation Decoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Martínez Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carles</namePart>
<namePart type="family">Creus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">España-Bonet</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 Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Popescu-Belis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loáiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>This work presents a decoding architecture that fuses the information from a neural translation model and the context semantics enclosed in a semantic space language model based on word embeddings. The method extends the beam search decoding process and therefore can be applied to any neural machine translation framework. With this, we sidestep two drawbacks of current document-level systems: (i) we do not modify the training process so there is no increment in training time, and (ii) we do not require document-level an-notated data. We analyze the impact of the fusion system approach and its parameters on the final translation quality for English–Spanish. We obtain consistent and statistically significant improvements in terms of BLEU and METEOR and we observe how the fused systems are able to handle synonyms to propose more adequate translations as well as help the system to disambiguate among several translation candidates for a word.</abstract>
<identifier type="citekey">martinez-garcia-etal-2019-context</identifier>
<identifier type="doi">10.18653/v1/D19-6502</identifier>
<location>
<url>https://aclanthology.org/D19-6502</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>13</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context-Aware Neural Machine Translation Decoding
%A Martínez Garcia, Eva
%A Creus, Carles
%A España-Bonet, Cristina
%Y Popescu-Belis, Andrei
%Y Loáiciga, Sharid
%Y Hardmeier, Christian
%Y Xiong, Deyi
%S Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F martinez-garcia-etal-2019-context
%X This work presents a decoding architecture that fuses the information from a neural translation model and the context semantics enclosed in a semantic space language model based on word embeddings. The method extends the beam search decoding process and therefore can be applied to any neural machine translation framework. With this, we sidestep two drawbacks of current document-level systems: (i) we do not modify the training process so there is no increment in training time, and (ii) we do not require document-level an-notated data. We analyze the impact of the fusion system approach and its parameters on the final translation quality for English–Spanish. We obtain consistent and statistically significant improvements in terms of BLEU and METEOR and we observe how the fused systems are able to handle synonyms to propose more adequate translations as well as help the system to disambiguate among several translation candidates for a word.
%R 10.18653/v1/D19-6502
%U https://aclanthology.org/D19-6502
%U https://doi.org/10.18653/v1/D19-6502
%P 13-23
Markdown (Informal)
[Context-Aware Neural Machine Translation Decoding](https://aclanthology.org/D19-6502) (Martínez Garcia et al., DiscoMT 2019)
ACL
- Eva Martínez Garcia, Carles Creus, and Cristina España-Bonet. 2019. Context-Aware Neural Machine Translation Decoding. In Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), pages 13–23, Hong Kong, China. Association for Computational Linguistics.