Machine Translation between Vietnamese and English: an Empirical Study
arXiv:1810.12557
Abstract
Machine translation is shifting to an end-to-end approach based on deep neural networks. The state of the art achieves impressive results for popular language pairs such as English - French or English - Chinese. However for English - Vietnamese the shortage of parallel corpora and expensive hyper-parameter search present practical challenges to neural-based approaches. This paper highlights our efforts on improving English-Vietnamese translations in two directions: (1) Building the largest open Vietnamese - English corpus to date, and (2) Extensive experiments with the latest neural models to achieve the highest BLEU scores. Our experiments provide practical examples of effectively employing different neural machine translation models with low-resource language pairs.
References in corpus (9)
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Deep Residual Learning for Image Recognition
- Convolutional Sequence to Sequence Learning
- Language Modeling with Gated Convolutional Networks
- Don't Decay the Learning Rate, Increase the Batch Size
- Neural Machine Translation in Linear Time
- Training Tips for the Transformer Model