Effective Strategies in Zero-Shot Neural Machine Translation
arXiv:1711.07893
Abstract
In this paper, we proposed two strategies which can be applied to a multilingual neural machine translation system in order to better tackle zero-shot scenarios despite not having any parallel corpus. The experiments show that they are effective in terms of both performance and computing resources, especially in multilingual translation of unbalanced data in real zero-resourced condition when they alleviate the language bias problem.
submitted to IWSLT17
Cited by in corpus (9)
- The Missing Ingredient in Zero-Shot Neural Machine Translation
- A Comprehensive Survey of Multilingual Neural Machine Translation
- Low-Resource Neural Machine Translation for Southern African Languages
- Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation
- Multilingual End-to-End Speech Translation
- Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
- Machine Translation with Unsupervised Length-Constraints
- Controlling Neural Machine Translation Formality with Synthetic Supervision
- Zero-shot Speech Translation