|
NMT's vocabulary
|
|
2
|
3540
|
February 7, 2018
|
|
Is there any efficient reference set(English) for bleu scoring?
|
|
2
|
1767
|
January 17, 2018
|
|
Word-level Distillation
|
|
1
|
2371
|
December 28, 2017
|
|
What is the use of Monolingual Corpora in SMT
|
|
2
|
2119
|
December 6, 2017
|
|
Training with out-of-domain data
|
|
0
|
1968
|
November 3, 2017
|
|
How is google's transformer translate between Chinese and English?
|
|
0
|
2010
|
November 1, 2017
|
|
Multiple translations open nmt
|
|
1
|
1812
|
October 31, 2017
|
|
Quality estimation / pred_score
|
|
3
|
2359
|
October 25, 2017
|
|
Paragraph vs sentence segmentation
|
|
2
|
3531
|
October 16, 2017
|
|
What is the best way to generate parallel corpus as per your past experience?
|
|
0
|
1718
|
September 26, 2017
|
|
In parallel corpus what should I keep, single sentence in each line or paragraph for MT?
|
|
2
|
1742
|
September 19, 2017
|
|
Metrics (Bleu, ppl, gold ppl, pred ....)
|
|
7
|
22067
|
September 14, 2017
|
|
About mask in attention layer and decoder
|
|
4
|
2841
|
September 12, 2017
|
|
How to create models that translate very quickly
|
|
7
|
4720
|
August 30, 2017
|
|
Exposure bias during training
|
|
3
|
3443
|
August 10, 2017
|
|
Improve BLEU by Coverage and Context Gate
|
|
6
|
2756
|
August 10, 2017
|
|
Use of Monolingual corpora in OPENNMT
|
|
7
|
4543
|
July 26, 2017
|
|
Using features for domain/client/subject adaptation
|
|
6
|
3072
|
July 12, 2017
|
|
Did someone test RNN with larger recurrence?
|
|
5
|
1949
|
June 23, 2017
|
|
Training chatbot with multiple inputs (to add context)
|
|
4
|
5276
|
June 22, 2017
|
|
Corpus compactization
|
|
2
|
2529
|
June 21, 2017
|
|
Incremental vocab
|
|
6
|
2541
|
June 21, 2017
|
|
Automatic training corpus filtering
|
|
15
|
5801
|
June 16, 2017
|
|
Implementing hashing to massively improve performance (by 95%)
|
|
0
|
1734
|
June 13, 2017
|
|
Speech-to-text using Convolutional LSTM layers
|
|
1
|
1889
|
June 8, 2017
|
|
Sentence length affect perplexity decrease
|
|
2
|
3093
|
June 2, 2017
|
|
Simple combination between SMT and NMT
|
|
0
|
2029
|
May 31, 2017
|
|
Alternative methods for <UNK> substitution
|
|
5
|
3368
|
May 29, 2017
|
|
Importance Sampling - training speed
|
|
1
|
2194
|
May 29, 2017
|
|
Weird Output after many attempts to train
|
|
0
|
1822
|
May 29, 2017
|