SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies

SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies” by Felix Stahlberg, Eva Hasler, Danielle Saunders, and William Byrne. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (Demo Papers), 2017. (5 pages).

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 ac- tively 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.

BibTeX entry:

@inproceedings{emnlp17:sgnmt,
   author = {Felix Stahlberg and Eva Hasler and Danielle Saunders and
	William Byrne},
   title = { {SGNMT} -- A Flexible {NMT} Decoding Platform for Quick
	Prototyping of New Models and Search Strategies},
   booktitle = {Proceedings of the 2017 Conference on Empirical Methods in
	Natural Language Processing (Demo Papers)},
   year = {2017},
   note = {(5 pages)},
   url = {http://aclweb.org/anthology/D/D17/D17-2005.pdf}
}

Back to Bill Byrne publications.