Flexible Non-Autoregressive Neural Machine Translation via Repositioning Edit Operations
We introduce an iterative text refinement model to reduce the decoding space of non-autoregressive models by disentangling the token prediction and relative position prediction. We show that our model achieves promising performance on the English-German translation task.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationPositionPredictionTranslationSimilar Papers 제목 키워드 기반
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints
We 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…
Imitation LearningMachine TranslationTranslationFelix: Flexible Text Editing Through Tagging and Insertion
We present Felix --- a flexible text-editing approach for generation, designed to derive the maximum benefit from the ideas of decoding with bi-directional contexts and self-supervised pre-training. In contrast to conven…
Automatic Post-EditingLanguage ModelingLanguage ModellingMachine Translation+4Levenshtein Transformer
Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transfor…
Automatic Post-EditingMachine TranslationText SummarizationTranslationEED: Extended Edit Distance Measure for Machine Translation
Over the years a number of machine translation metrics have been developed in order to evaluate the accuracy and quality of machine-generated translations. Metrics such as BLEU and TER have been used for decades. However…
Machine TranslationTranslationReinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation
Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT). However, a performance gap exists between NAR and autoregressive models due to the large decoding space and di…
Machine TranslationNMTreinforcement-learningReinforcement Learning (RL)+1