|
OpenNMT-tf Fine tuning base model gives worse and decreases BLEU scores
|
|
8
|
1661
|
December 5, 2018
|
|
Handle numbers, urls, dates
|
|
2
|
2006
|
December 5, 2018
|
|
TransformerBig model - GTX 1080 Ti (11G) - ResourceExhaustedError
|
|
8
|
3112
|
December 5, 2018
|
|
Use GloVe with concatenated word features (OpenNMT-py)
|
|
0
|
913
|
December 5, 2018
|
|
Tokenization OpenNMT-tf
|
|
3
|
903
|
December 4, 2018
|
|
Using multiple gpus in training.py
|
|
4
|
3034
|
December 1, 2018
|
|
Translation server in OpenNMT-tf
|
|
2
|
1012
|
November 30, 2018
|
|
Perplexity in opennmt-tf
|
|
1
|
1110
|
November 30, 2018
|
|
Alignment not coming properly
|
|
1
|
993
|
November 30, 2018
|
|
OpenNMT-tf Distributed Training - Processes don't end after training completes
|
|
4
|
1047
|
November 29, 2018
|
|
OpenNMT-tf serving with latest prediction_service_pb2_grpc for translation
|
|
2
|
2511
|
November 28, 2018
|
|
What is the relationship between ppl, accuracy and bleu scores in machine translation? In my experiment, although ppl and accuracy on the validationset are greatly improved, Bleu scores is reduced
|
|
0
|
3132
|
November 25, 2018
|
|
Hi , I have 130k train src tgt pairs, but the log info of training process shows that there are only 22k train pairs after we preprocess the data
|
|
4
|
1024
|
November 25, 2018
|
|
Issues when running the English-German WMT15 training
|
|
22
|
5279
|
November 22, 2018
|
|
Issue in using distributed training in openNMT-TF
|
|
31
|
3325
|
November 21, 2018
|
|
Beam Search with target words features: how does it work?
|
|
3
|
955
|
November 21, 2018
|
|
Generating learning curves using OpenNMT-py version
|
|
2
|
1182
|
November 21, 2018
|
|
Opnenmt-th takes so long to load training data before it really starts the training process
|
|
2
|
903
|
November 21, 2018
|
|
Learning rate reduced to 0 after start_decay_steps values
|
|
3
|
2099
|
November 21, 2018
|
|
Questions on large batch size training with Transformer in low-resource scenario
|
|
2
|
4180
|
November 19, 2018
|
|
I have question about the transformer in SubLayerConnection, is the code wrong?
|
|
2
|
1051
|
November 19, 2018
|
|
How to change the data parallelism to model parallelsim?
|
|
2
|
969
|
November 19, 2018
|
|
Translate.py runs faster on CPU than GPU
|
|
0
|
1010
|
November 2, 2018
|
|
Speech to text - Memory error
|
|
1
|
824
|
November 19, 2018
|
|
Training fails on Multi GPU with Torch
|
|
2
|
859
|
November 19, 2018
|
|
Opennmt py rest server
|
|
1
|
1021
|
November 19, 2018
|
|
How can I decide vocabulary size for given corpus size?
|
|
1
|
2984
|
November 19, 2018
|
|
Is there a paper to cite if OpenNMT is used in sequence mapping tasks other than neural machine translation?
|
|
1
|
859
|
November 16, 2018
|
|
Server always returning empty list
|
|
6
|
1796
|
November 16, 2017
|
|
OpenNMT-tf - how to use alignments and phares tables
|
|
11
|
3323
|
November 14, 2018
|