@inproceedings{jean-cho-2020-log,
title = "Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation",
author = "Jean, S{\'e}bastien and
Cho, Kyunghyun",
editor = "Agrawal, Priyanka and
Kozareva, Zornitsa and
Kreutzer, Julia and
Lampouras, Gerasimos and
Martins, Andr{\'e} and
Ravi, Sujith and
Vlachos, Andreas",
booktitle = "Proceedings of the Fourth Workshop on Structured Prediction for NLP",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.spnlp-1.11",
doi = "10.18653/v1/2020.spnlp-1.11",
pages = "95--101",
abstract = "We seek to maximally use various data sources, such as parallel and monolingual data, to build an effective and efficient document-level translation system. In particular, we start by considering a noisy channel approach (CITATION) that combines a target-to-source translation model and a language model. By applying Bayes{'} rule strategically, we reformulate this approach as a log-linear combination of translation, sentence-level and document-level language model probabilities. In addition to using static coefficients for each term, this formulation alternatively allows for the learning of dynamic per-token weights to more finely control the impact of the language models. Using both static or dynamic coefficients leads to improvements over a context-agnostic baseline and a context-aware concatenation model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jean-cho-2020-log">
<titleInfo>
<title>Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sébastien</namePart>
<namePart type="family">Jean</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Structured Prediction for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Kreutzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Lampouras</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">Sujith</namePart>
<namePart type="family">Ravi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We seek to maximally use various data sources, such as parallel and monolingual data, to build an effective and efficient document-level translation system. In particular, we start by considering a noisy channel approach (CITATION) that combines a target-to-source translation model and a language model. By applying Bayes’ rule strategically, we reformulate this approach as a log-linear combination of translation, sentence-level and document-level language model probabilities. In addition to using static coefficients for each term, this formulation alternatively allows for the learning of dynamic per-token weights to more finely control the impact of the language models. Using both static or dynamic coefficients leads to improvements over a context-agnostic baseline and a context-aware concatenation model.</abstract>
<identifier type="citekey">jean-cho-2020-log</identifier>
<identifier type="doi">10.18653/v1/2020.spnlp-1.11</identifier>
<location>
<url>https://aclanthology.org/2020.spnlp-1.11</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>95</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation
%A Jean, Sébastien
%A Cho, Kyunghyun
%Y Agrawal, Priyanka
%Y Kozareva, Zornitsa
%Y Kreutzer, Julia
%Y Lampouras, Gerasimos
%Y Martins, André
%Y Ravi, Sujith
%Y Vlachos, Andreas
%S Proceedings of the Fourth Workshop on Structured Prediction for NLP
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F jean-cho-2020-log
%X We seek to maximally use various data sources, such as parallel and monolingual data, to build an effective and efficient document-level translation system. In particular, we start by considering a noisy channel approach (CITATION) that combines a target-to-source translation model and a language model. By applying Bayes’ rule strategically, we reformulate this approach as a log-linear combination of translation, sentence-level and document-level language model probabilities. In addition to using static coefficients for each term, this formulation alternatively allows for the learning of dynamic per-token weights to more finely control the impact of the language models. Using both static or dynamic coefficients leads to improvements over a context-agnostic baseline and a context-aware concatenation model.
%R 10.18653/v1/2020.spnlp-1.11
%U https://aclanthology.org/2020.spnlp-1.11
%U https://doi.org/10.18653/v1/2020.spnlp-1.11
%P 95-101
Markdown (Informal)
[Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation](https://aclanthology.org/2020.spnlp-1.11) (Jean & Cho, spnlp 2020)
ACL