SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
Conference on Empirical Methods in Natural Language Processing
Association for Computational Linguistics
MetadataShow full item record
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. http://aclweb.org/anthology/D/D17/D17-2005.pdf
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.
This work was supported by the U.K. Engineering and Physical Sciences Research Council (EPSRC grant EP/L027623/1).
External link: http://aclweb.org/anthology/D/D17/D17-2005.pdf
This record's URL: https://www.repository.cam.ac.uk/handle/1810/267366