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

TL;DR

SGNMT is a flexible, modular platform designed for rapid prototyping of neural machine translation models and search strategies, facilitating research and development in the field.

Contribution

The paper presents SGNMT, a novel platform that simplifies integration of diverse predictors and search algorithms for machine translation research.

Findings

Enables quick prototyping of new models and strategies

Supports complex predictor combinations and search methods

Widely adopted in academic research and education

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.