SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
View / Open Files
Authors
Stahlberg, F
Hasler, E
Saunders, D
Byrne, W
Publication Date
2017-09-09Conference Name
Conference on Empirical Methods in Natural Language Processing
Publisher
Association for Computational Linguistics
Language
English
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Stahlberg, F., Hasler, E., Saunders, D., & Byrne, W. (2017). SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies. Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.17863/CAM.12005
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.
Sponsorship
This work was supported by the U.K. Engineering and Physical Sciences Research Council (EPSRC grant EP/L027623/1).
Funder references
Engineering and Physical Sciences Research Council (EP/L027623/1)
Identifiers
External DOI: https://doi.org/10.17863/CAM.12005
This record's URL: https://www.repository.cam.ac.uk/handle/1810/267366
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.