Issue #118 – EDITOR: a Repositioning Transformer with Soft Lexical Constraints
18 Feb21
Issue #118 – EDITOR: a Repositioning Transformer with Soft Lexical Constraints
Author: Dr. Karin Sim, Machine Translation Scientist @ Iconic
EDITOR: an Edit-Based Transformer with Repositioning for Neural MT with Soft Lexical Constraints
Introduction
On our blog a couple of weeks ago (issue 116), Patrik explored fully non-autoregressive machine translation, highlighting the tricks such as dependency reduction that enabled quality to be maintained while retaining the speed-up gains over autoregressive MT. Today we revisit non-autoregressive translation (NAT), examining EDITOR by Xu and Carpuat (2020) which builds on the Levenshtein Transformer (see issues 82 and 86 for a recap), to bring both faster decoding and improvements in translation quality.
In a nutshell
EDITOR introduces a new reposition operation which is more effective and