Feel free add to this, via a pull request
- 15 project names include nmt
- 5 project names include seq2seq
- 2 project names include dl4mt
- 3 projects are derived from Kyunghyun Cho's tutorial at the 2015 DL4MT winter school
Caffe2-based NMT
| Software | Who | Comments |
|---|---|---|
| seq2seq | Deepak, Yury |
Chainer-based NMT
| Software | Who | Comments |
|---|---|---|
| chainn | Philip | |
| KyotoNMT | Fabien | |
| attention_is_all_you_need | Sosuke | impements Google's pure attention model |
| Software | Who | Comments |
|---|---|---|
| EUREKA-MangoNMT | Jiajun | |
| Mantidae | Cong | A successor of Mantis |
| Marian | Marcin, Tomasz | Compatible with Nematus models |
| N3LP | Kazuma, Akiko | |
| Zoph_RNN | Barret | Supports multi-GPU parallelism |
DyNet-based NMT
| Software | Who | Comments |
|---|---|---|
| dynmt-py | Roee | |
| lamtram | Graham | |
| mantis | Trevor | |
| NMTKit | Yusuke | |
| xnmt | NeuLab |
Keras-based NMT
| Software | Who | Comments |
|---|---|---|
| Keras seq2seq | Fariz | |
| NMT-Keras | Álvaro |
MXNet-based NMT
| Software | Who | Comments |
|---|---|---|
| MXNMT | magic282 | |
| sockeye | AWS Labs |
PyTorch-based NMT
| Software | Who | Comments |
|---|---|---|
| OpenNMT-py | Harvard, Systran |
TensorFlow-based NMT
| Software | Who | Comments |
|---|---|---|
| byteNet-tensorflow | Paarth | |
| bytenet_translation | Kyubyong | |
| Neural Monkey | ÚFAL | |
| seq2seq | Alexandre | |
| Tensor2Tensor | Implements many models | |
| tf-seq2seq | Denny | See also tutorial |
Theano-based NMT
| Software | Who | Comments |
|---|---|---|
| DCNMT | SwordYork | |
| dl4mt-tutorial | Cho, Orhan | |
| dl4mt-c2c | Jason, Cho | |
| HNMT | Robert | |
| Nematus | Rico, Cho, Orhan | |
| neuralmt | Raphael | |
| NMT | Zhaopeng | Adds coverage and context gate |
| nmtpy | LIUM | refactored dl4mt-tutorial |
| RNNsearch | Playinf, Xiamen University | |
| SGNMT | Cambridge | Syntactically-guided NMT |
| THUMT | Tsinghua University |
Torch-based NMT
| Software | Who | Comments |
|---|---|---|
| nmt-android | Yoon, Sasha | |
| seq2seq-attn | Yoon | Superseded by OpenNMT, except for character-level stuff |
| OpenNMT | Harvard, Systran | |
| fairseq | Novel CNN+attention |
| Software | Who | Backend | Comments |
|---|---|---|---|
| nmt.hybrid | Thang | Matlab | also word-based |
| Paddle | Baidu | Paddle | demo |
| textsum | TensorFlow | text summarization demo using seq2seq+attn |