Neural Machine Translation: A Review and Survey

Stahlberg, Felix

doi:10.48550/arxiv.1912.02047

Cited by 1 publication

(1 citation statement)

References 441 publications

(628 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural models have been revolutionising machine translation (MT), and have achieved state-of-the-art for many high-resource language pairs (Chen et al, 2018;Stahlberg, 2019;Maruf et al, 2019). However, the scarcity of bilingual parallel corpora is still a major challenge for training high-quality NMT models (Koehn and Knowles, 2017).…”

Section: Introductionmentioning

confidence: 99%

Collective Wisdom: Improving Low-resource Neural Machine Translation using Adaptive Knowledge Distillation

Saleh¹,

Buntine²,

Haffari³

2020

Preprint

View full text Add to dashboard Cite

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model trained on a high-resource language-pair and fine-tuning it on the data of the low-resource MT condition of interest. However, it is not clear generally which high-resource language-pair offers the best transfer learning for the target MT setting. Furthermore, different transferred models may have complementary semantic and/or syntactic strengths, hence using only one model may be sub-optimal. In this paper, we tackle this problem using knowledge distillation, where we propose to distill the knowledge of ensemble of teacher models to a single student model. As the quality of these teacher models varies, we propose an effective adaptive knowledge distillation approach to dynamically adjust the contribution of the teacher models during the distillation process. Experiments on transferring from a collection of six language pairs from IWSLT to five low-resource language-pairs from TED Talks demonstrate the effectiveness of our approach, achieving up to +0.9 BLEU score improvement compared to strong baselines.

show abstract