Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation
This work presents a tool that facilitates machine translation research and education, but it is incremental as it builds on existing decoding methods without introducing new paradigms.
The paper describes SGNMT, a versatile decoding platform for machine translation that integrates neural models with constraints and symbolic models, and highlights its applications in teaching, research, and technology transfer, such as its use in a Cambridge MPhil course and in SDL plc's products.
SGNMT is a decoding platform for machine translation which allows paring various modern neural models of translation with different kinds of constraints and symbolic models. In this paper, we describe three use cases in which SGNMT is currently playing an active role: (1) teaching as SGNMT is being used for course work and student theses in the MPhil in Machine Learning, Speech and Language Technology at the University of Cambridge, (2) research as most of the research work of the Cambridge MT group is based on SGNMT, and (3) technology transfer as we show how SGNMT is helping to transfer research findings from the laboratory to the industry, eg. into a product of SDL plc.