paper-with-me

홈 › Papers

End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification

2018-11-12 · Jindřich Libovický, Jindřich Helcl

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in parallel. We present a novel non-autoregressive architecture based on connectionist temporal classification and evaluate it on the task of neural machine translation. Unlike other non-autoregressive methods which operate in several steps, our model can be trained end-to-end. We conduct experiments on the WMT English-Romanian and English-German datasets. Our models achieve a significant speedup over the autoregressive models, keeping the translation quality comparable to other non-autoregressive models.

📄 PDF Abstract BibTeX arXiv:1811.04719

Code (1)

m3yrin/nar-latent-alignment pytorch

Tasks

DecoderGeneral ClassificationMachine TranslationTranslation

Similar Papers 제목 키워드 기반

End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification

2018-10-01 · EMNLP 2018 10 · Jind{\v{r}}ich Libovick{\'y}, Jind{\v{r}}ich Helcl

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols indep…

DecoderGeneral ClassificationMachine TranslationTranslation

Improving Fluency of Non-Autoregressive Machine Translation

2020-04-07 · Zdeněk Kasner, Jindřich Libovický, Jindřich Helcl

Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a …

Machine TranslationTranslation

CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task

2022-12-01 · Jindřich Helcl

We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autore…

Translation

Can Multilinguality benefit Non-autoregressive Machine Translation?

2021-12-16 · Sweta Agrawal, Julia Kreutzer, Colin Cherry

Non-autoregressive (NAR) machine translation has recently achieved significant improvements, and now outperforms autoregressive (AR) models on some benchmarks, providing an efficient alternative to AR inference. However,…

Machine TranslationTranslation

Can Multilinguality Benefit Non-autoregressive Machine Translation?

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Non-autoregressive (NAR) machine translation has recently achieved significant improvements, and now outperforms autoregressive (AR) models on some benchmarks, providing an efficient alternative to AR inference. However,…

Machine TranslationTranslation