A Study of Multilingual Neural Machine Translation
arXiv:1912.11625
Abstract
Multilingual neural machine translation (NMT) has recently been investigated from different aspects (e.g., pivot translation, zero-shot translation, fine-tuning, or training from scratch) and in different settings (e.g., rich resource and low resource, one-to-many, and many-to-one translation). This paper concentrates on a deep understanding of multilingual NMT and conducts a comprehensive study on a multilingual dataset with more than 20 languages. Our results show that (1) low-resource language pairs benefit much from multilingual training, while rich-resource language pairs may get hurt under limited model capacity and training with similar languages benefits more than dissimilar languages; (2) fine-tuning performs better than training from scratch in the one-to-many setting while training from scratch performs better in the many-to-one setting; (3) the bottom layers of the encoder and top layers of the decoder capture more language-specific information, and just fine-tuning these parts can achieve good accuracy for low-resource language pairs; (4) direct translation is better than pivot translation when the source language is similar to the target language (e.g., in the same language branch), even when the size of direct training data is much smaller; (5) given a fixed training data budget, it is better to introduce more languages into multilingual training for zero-shot translation.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Convolutional Sequence to Sequence Learning
- MASS: Masked Sequence to Sequence Pre-training for Language Generation
- Achieving Human Parity on Automatic Chinese to English News Translation
- Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
- Multilingual Neural Machine Translation with Knowledge Distillation
- A Teacher-Student Framework for Zero-Resource Neural Machine Translation
- Multi-task Sequence to Sequence Learning
- Zero-Resource Translation with Multi-Lingual Neural Machine Translation
- Rapid Adaptation of Neural Machine Translation to New Languages
- Contextual Parameter Generation for Universal Neural Machine Translation
- Multilingual Neural Machine Translation with Language Clustering
- Language Graph Distillation for Low-Resource Machine Translation