Semantic Structural Decomposition for Neural Machine Translation

Code

• github.com/eliorsulem/semantic-structural-decomposition-for-nmt
  OfficialIn papernone★ 1

Abstract

Building on recent advances in semantic parsing and text simplification, we investigate the use of semantic splitting of the source sentence as preprocessing for machine translation. We experiment with a Transformer model and evaluate using large-scale crowd-sourcing experiments. Results show a significant increase in fluency on long sentences on an English-to- French setting with a training corpus of 5M sentence pairs, while retaining comparable adequacy. We also perform a manual analysis which explores the tradeoff between adequacy and fluency in the case where all sentence lengths are considered.

Tasks

Reproductions