@inproceedings{lam-etal-2018-reinforcement,
title = "A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation",
author = "Lam, Tsz Kin and
Kreutzer, Julia and
Riezler, Stefan",
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.17",
pages = "189--198",
abstract = "We present an approach to interactivepredictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial translations. Secondly, human effort is further reduced by using the entropy of word predictions as uncertainty criterion to trigger feedback requests. Lastly, online updates of the model parameters after every interaction allow the model to adapt quickly. We show in simulation experiments that reward signals on partial translations significantly improve character F-score and BLEU compared to feedback on full translations only, while human effort can be reduced to an average number of 5 feedback requests for every input.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lam-etal-2018-reinforcement">
<titleInfo>
<title>A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsz</namePart>
<namePart type="given">Kin</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Kreutzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Riezler</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>We present an approach to interactivepredictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial translations. Secondly, human effort is further reduced by using the entropy of word predictions as uncertainty criterion to trigger feedback requests. Lastly, online updates of the model parameters after every interaction allow the model to adapt quickly. We show in simulation experiments that reward signals on partial translations significantly improve character F-score and BLEU compared to feedback on full translations only, while human effort can be reduced to an average number of 5 feedback requests for every input.</abstract>
<identifier type="citekey">lam-etal-2018-reinforcement</identifier>
<location>
<url>https://aclanthology.org/2018.eamt-main.17</url>
</location>
<part>
<date>2018-05</date>
<extent unit="page">
<start>189</start>
<end>198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
%A Lam, Tsz Kin
%A Kreutzer, Julia
%A Riezler, Stefan
%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 lam-etal-2018-reinforcement
%X We present an approach to interactivepredictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial translations. Secondly, human effort is further reduced by using the entropy of word predictions as uncertainty criterion to trigger feedback requests. Lastly, online updates of the model parameters after every interaction allow the model to adapt quickly. We show in simulation experiments that reward signals on partial translations significantly improve character F-score and BLEU compared to feedback on full translations only, while human effort can be reduced to an average number of 5 feedback requests for every input.
%U https://aclanthology.org/2018.eamt-main.17
%P 189-198
Markdown (Informal)
[A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation](https://aclanthology.org/2018.eamt-main.17) (Lam et al., EAMT 2018)
ACL