@inproceedings{stahlberg-etal-2017-sgnmt,
title = "{SGNMT} {--} A Flexible {NMT} Decoding Platform for Quick Prototyping of New Models and Search Strategies",
author = "Stahlberg, Felix and
Hasler, Eva and
Saunders, Danielle and
Byrne, Bill",
editor = "Specia, Lucia and
Post, Matt and
Paul, Michael",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-2005",
doi = "10.18653/v1/D17-2005",
pages = "25--30",
abstract = "This paper introduces SGNMT, our experimental platform for machine translation research. SGNMT provides a generic interface to neural and symbolic scoring modules (predictors) with left-to-right semantic such as translation models like NMT, language models, translation lattices, n-best lists or other kinds of scores and constraints. Predictors can be combined with other predictors to form complex decoding tasks. SGNMT implements a number of search strategies for traversing the space spanned by the predictors which are appropriate for different predictor constellations. Adding new predictors or decoding strategies is particularly easy, making it a very efficient tool for prototyping new research ideas. SGNMT is actively being used by students in the MPhil program in Machine Learning, Speech and Language Technology at the University of Cambridge for course work and theses, as well as for most of the research work in our group.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stahlberg-etal-2017-sgnmt">
<titleInfo>
<title>SGNMT – A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Stahlberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Hasler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Saunders</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="family">Byrne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces SGNMT, our experimental platform for machine translation research. SGNMT provides a generic interface to neural and symbolic scoring modules (predictors) with left-to-right semantic such as translation models like NMT, language models, translation lattices, n-best lists or other kinds of scores and constraints. Predictors can be combined with other predictors to form complex decoding tasks. SGNMT implements a number of search strategies for traversing the space spanned by the predictors which are appropriate for different predictor constellations. Adding new predictors or decoding strategies is particularly easy, making it a very efficient tool for prototyping new research ideas. SGNMT is actively being used by students in the MPhil program in Machine Learning, Speech and Language Technology at the University of Cambridge for course work and theses, as well as for most of the research work in our group.</abstract>
<identifier type="citekey">stahlberg-etal-2017-sgnmt</identifier>
<identifier type="doi">10.18653/v1/D17-2005</identifier>
<location>
<url>https://aclanthology.org/D17-2005</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>25</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SGNMT – A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
%A Stahlberg, Felix
%A Hasler, Eva
%A Saunders, Danielle
%A Byrne, Bill
%Y Specia, Lucia
%Y Post, Matt
%Y Paul, Michael
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F stahlberg-etal-2017-sgnmt
%X This paper introduces SGNMT, our experimental platform for machine translation research. SGNMT provides a generic interface to neural and symbolic scoring modules (predictors) with left-to-right semantic such as translation models like NMT, language models, translation lattices, n-best lists or other kinds of scores and constraints. Predictors can be combined with other predictors to form complex decoding tasks. SGNMT implements a number of search strategies for traversing the space spanned by the predictors which are appropriate for different predictor constellations. Adding new predictors or decoding strategies is particularly easy, making it a very efficient tool for prototyping new research ideas. SGNMT is actively being used by students in the MPhil program in Machine Learning, Speech and Language Technology at the University of Cambridge for course work and theses, as well as for most of the research work in our group.
%R 10.18653/v1/D17-2005
%U https://aclanthology.org/D17-2005
%U https://doi.org/10.18653/v1/D17-2005
%P 25-30
Markdown (Informal)
[SGNMT – A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies](https://aclanthology.org/D17-2005) (Stahlberg et al., EMNLP 2017)
ACL