Goal:
+train an efficient universal model that can translate b/n any language
Progress:
+
work sets a new milestone towards building a single model
Massively Multilingual Neural Machine Translation
in the Wild: Findings and Challenges https://arxiv.org/pdf/1907.05019.pdf
@fbk_mt
+train an efficient universal model that can translate b/n any language
Progress:
+

Massively Multilingual Neural Machine Translation
in the Wild: Findings and Challenges https://arxiv.org/pdf/1907.05019.pdf
@fbk_mt

Languages in total: 103, can result > 10k translation directions.
Training examples: 25Billion
Core points:
- transfer-learning ability across languages
- benefits low-resource languages
- keeps performance of high-resource languages
- detailed analysis on model training
Training examples: 25Billion
Core points:
- transfer-learning ability across languages
- benefits low-resource languages
- keeps performance of high-resource languages
- detailed analysis on model training

Open problems areas as mentioned in the paper:
- Data & supervision
- Learning
- Model capacity
- Arch & Vocab
Continues ...
- Data & supervision
- Learning
- Model capacity
- Arch & Vocab
Continues ...