Boosting Neural Machine Translation
Not on the map. Why?
Abstract (arXiv)
Training efficiency is one of the main problems for Neural Machine Translation (NMT). Deep networks need for very large data as well as many training iterations to achieve state-of-the-art performance. This results in very high computation cost, slowing down research and industrialisation. In this paper, we propose to alleviate this problem with several training methods based on data boosting and bootstrap with no modifications to the neural network. It imitates the learning process of humans, which typically spend more time when learning "difficult" concepts than easier ones. We experiment on an English-French translation task showing accuracy improvements of up to 1.63 BLEU while saving 20% of training time.
Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Dec 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 0; 2023: 2.
4 papers.
- 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
- 2021Exploiting Curriculum Learning in Unsupervised Neural Machine Translationcited by 6
- 2023Separating the Wheat from the Chaff with BREAD: An open-source benchmark and metrics to detect redundancy in textcited by 1
- 2023Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translationcited by 0
- 2023Separating the Wheat from the Chaff with BREAD: An open-source benchmark and metrics to detect redundancy in text11 Nov 2023
- 2023Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation6 Sep 2023
- 2021Exploiting Curriculum Learning in Unsupervised Neural Machine Translation23 Sep 2021
- 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey14 Apr 2021