Feature Requests


Support other forms of dropout/regularization (9)
Minimum Risk Training for NMT (1)
Ensemble translation (3)
A w2v-coupled training procedure (1)
Model compression via weight tying (2)
Pre-trained/fixed embeddings for features (1)
Multi-Source Translation (6)
Support n_best option for CTranslate (5)
It will be better if there is a Coverage Attention Module (3)
Same source/target embeddings for intralingual task (3)
Creating phrase tables out of alignment output for translating UNKs (3)
Multi function REST API (3)
Support of Translation History (1)
External reward signal for human-in-the-loop training (3)
Use CuDNN RNN for faster training (2)
Larger scale monolingual resource for target language (2)
Variable Dropout setting (4)
Implement Copy Mechanism (5)
Support shard training (1)
Variable size features (3)
Seq2seq pretraining (1)
Large Vocabulary model (2)
Control translation length (6)
Differentiable memory (2)
Character-Aware Models (1)