mlsanityData to 14 Oct 2026

Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer

arXiv 2109.13097 ↗First posted 27 Sep 2021cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high resource source-pivot and pivot-target language pairs and an individual system is trained for both sub-tasks. However, these models have no connection during training, and the source-pivot model is not optimized to produce the best translation for the source-target task. In this work, we propose to train a pivot-based NMT system with the reinforcement learning (RL) approach, which has been investigated for various text generation tasks, including machine translation (MT). We utilize a non-autoregressive transformer and present an end-to-end pivot-based integrated model, enabling training on source-target data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

18 of 37 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  5. 2016Sequence-Level Knowledge Distillationcited by 801
  6. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  7. 2015Sequence Level Training with Recurrent Neural Networkscited by 576
  8. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  9. 2017Non-Autoregressive Neural Machine Translationcited by 463
  10. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  11. 2019Massively Multilingual Neural Machine Translationcited by 246
  12. 2020The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MTcited by 128
6 more
  1. 2019Understanding Knowledge Distillation in Non-autoregressive Machine Translationcited by 122
  2. 2015Minimum Risk Training for Neural Machine Translationcited by 115
  3. 2019On the Weaknesses of Reinforcement Learning for Neural Machine Translationcited by 82
  4. 2018A Study of Reinforcement Learning for Neural Machine Translationcited by 74
  5. 2019Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languagescited by 36
  6. 2016Neural Machine Translation with Pivot Languagescited by 25

Built on by

Not cited yet.