Semantic structural decomposition for neural machine translation

Elior Sulem, Omri Abend, Ari Rappoport

Research output: Contribution to conferencePaperpeer-review


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.
Original languageEnglish
Number of pages8
StatePublished - Dec 2020
Externally publishedYes


Dive into the research topics of 'Semantic structural decomposition for neural machine translation'. Together they form a unique fingerprint.

Cite this