|
Further Memory Optimization
|
|
0
|
1978
|
June 1, 2017
|
|
Translation of complex numbers
|
|
4
|
3720
|
June 1, 2017
|
|
What is the Kaldi input format? Where can I find an example or definition?
|
|
3
|
1849
|
June 1, 2017
|
|
OpenNMT v0.7 release
|
|
7
|
3303
|
June 1, 2017
|
|
LSTM based seq2seq generate 0, the padding token
|
|
0
|
2056
|
May 31, 2017
|
|
How to reset the learning rate?
|
|
3
|
2727
|
May 31, 2017
|
|
Simple combination between SMT and NMT
|
|
0
|
1992
|
May 31, 2017
|
|
Alternative methods for <UNK> substitution
|
|
5
|
3289
|
May 29, 2017
|
|
Bpe for chinese characters?
|
|
5
|
5087
|
May 30, 2017
|
|
Bpe encode with translation_server.lua
|
|
1
|
2302
|
May 30, 2017
|
|
Importance Sampling - training speed
|
|
1
|
2144
|
May 29, 2017
|
|
Learning English compound nouns
|
|
10
|
3862
|
May 29, 2017
|
|
Weird Output after many attempts to train
|
|
0
|
1777
|
May 29, 2017
|
|
Strange behaviour of rest_translation_server.lua
|
|
3
|
1356
|
May 27, 2017
|
|
Torch/nn update breaks loading OpenNMT models trained with earlier version(?)
|
|
6
|
3020
|
May 26, 2017
|
|
Coding environment for the framework
|
|
1
|
1492
|
May 26, 2017
|
|
Out of memory when translating?
|
|
9
|
3411
|
May 23, 2017
|
|
ZH->EN uppercased the second word of the sentence?
|
|
6
|
2670
|
May 19, 2017
|
|
Is there a way to tell not to check part of sentence
|
|
1
|
1283
|
May 19, 2017
|
|
The error when continuing a training
|
|
1
|
1497
|
May 17, 2017
|
|
The warning of nccl
|
|
2
|
2754
|
May 17, 2017
|
|
Validating trained model
|
|
6
|
2407
|
May 16, 2017
|
|
The WMT14 English-French result on the Opennmt-py
|
|
3
|
2276
|
May 16, 2017
|
|
Weight table:set weight of some vocabulary
|
|
5
|
2702
|
May 15, 2017
|
|
Output from CTranslate and OpenNMT translate differ
|
|
2
|
1768
|
May 14, 2017
|
|
CJK tokenizer question
|
|
0
|
1500
|
May 12, 2017
|
|
How to use new feature:target_subdict
|
|
2
|
1716
|
May 9, 2017
|
|
Mini batch size
|
|
3
|
4900
|
May 5, 2017
|
|
Could OpenNMT run on the MAC OXS?
|
|
8
|
3131
|
May 5, 2017
|
|
Incremental training - size of new training data and vocabulary updating
|
|
2
|
3032
|
May 4, 2017
|