Левенштейн трансформері
Related Papers
Lexically Constrained Neural Machine Translation with Levenshtein Transformer
AbstractThis paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them …...
EDITOR: An Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints
AbstractWe introduce an Edit-Based TransfOrmer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice. Building on recent models for non-autoregressive …...
Levenshtein Training for Word-level Quality Estimation
AbstractWe propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to …...
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task
AbstractThis paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared task, focusing on the …...