@inproceedings{agrawal-etal-2018-contextual,
title = "Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides",
author = "Agrawal, Ruchit and
Turchi, Marco and
Negri, Matteo",
editor = "P{\'e}rez-Ortiz, Juan Antonio and
S{\'a}nchez-Mart{\'\i}nez, Felipe and
Espl{\`a}-Gomis, Miquel and
Popovi{\'c}, Maja and
Rico, Celia and
Martins, Andr{\'e} and
Van den Bogaert, Joachim and
Forcada, Mikel L.",
booktitle = "Proceedings of the 21st Annual Conference of the European Association for Machine Translation",
month = may,
year = "2018",
address = "Alicante, Spain",
url = "https://aclanthology.org/2018.eamt-main.1",
pages = "31--40",
abstract = "A salient feature of Neural Machine Translation (NMT) is the end-to-end nature of training employed, eschewing the need of separate components to model different linguistic phenomena. Rather, an NMT model learns to translate individual sentences from the labeled data itself. However, traditional NMT methods trained on large parallel corpora with a one-to-one sentence mapping make an implicit assumption of sentence independence. This makes it challenging for current NMT systems to model inter-sentential discourse phenomena. While recent research in this direction mainly leverages a single previous source sentence to model discourse, this paper proposes the incorporation of a context window spanning previous as well as next sentences as source-side context and previously generated output as target-side context, using an effective non-recurrent architecture based on self-attention. Experiments show improvement over non-contextual models as well as contextual methods using only previous context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agrawal-etal-2018-contextual">
<titleInfo>
<title>Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruchit</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Pérez-Ortiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Sánchez-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Celia</namePart>
<namePart type="family">Rico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Van den Bogaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">Alicante, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A salient feature of Neural Machine Translation (NMT) is the end-to-end nature of training employed, eschewing the need of separate components to model different linguistic phenomena. Rather, an NMT model learns to translate individual sentences from the labeled data itself. However, traditional NMT methods trained on large parallel corpora with a one-to-one sentence mapping make an implicit assumption of sentence independence. This makes it challenging for current NMT systems to model inter-sentential discourse phenomena. While recent research in this direction mainly leverages a single previous source sentence to model discourse, this paper proposes the incorporation of a context window spanning previous as well as next sentences as source-side context and previously generated output as target-side context, using an effective non-recurrent architecture based on self-attention. Experiments show improvement over non-contextual models as well as contextual methods using only previous context.</abstract>
<identifier type="citekey">agrawal-etal-2018-contextual</identifier>
<location>
<url>https://aclanthology.org/2018.eamt-main.1</url>
</location>
<part>
<date>2018-05</date>
<extent unit="page">
<start>31</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides
%A Agrawal, Ruchit
%A Turchi, Marco
%A Negri, Matteo
%Y Pérez-Ortiz, Juan Antonio
%Y Sánchez-Martínez, Felipe
%Y Esplà-Gomis, Miquel
%Y Popović, Maja
%Y Rico, Celia
%Y Martins, André
%Y Van den Bogaert, Joachim
%Y Forcada, Mikel L.
%S Proceedings of the 21st Annual Conference of the European Association for Machine Translation
%D 2018
%8 May
%C Alicante, Spain
%F agrawal-etal-2018-contextual
%X A salient feature of Neural Machine Translation (NMT) is the end-to-end nature of training employed, eschewing the need of separate components to model different linguistic phenomena. Rather, an NMT model learns to translate individual sentences from the labeled data itself. However, traditional NMT methods trained on large parallel corpora with a one-to-one sentence mapping make an implicit assumption of sentence independence. This makes it challenging for current NMT systems to model inter-sentential discourse phenomena. While recent research in this direction mainly leverages a single previous source sentence to model discourse, this paper proposes the incorporation of a context window spanning previous as well as next sentences as source-side context and previously generated output as target-side context, using an effective non-recurrent architecture based on self-attention. Experiments show improvement over non-contextual models as well as contextual methods using only previous context.
%U https://aclanthology.org/2018.eamt-main.1
%P 31-40
Markdown (Informal)
[Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides](https://aclanthology.org/2018.eamt-main.1) (Agrawal et al., EAMT 2018)
ACL