|
NMT's vocabulary
|
|
2
|
3051
|
February 7, 2018
|
|
Is there any efficient reference set(English) for bleu scoring?
|
|
2
|
1477
|
January 17, 2018
|
|
Word-level Distillation
|
|
1
|
1940
|
December 28, 2017
|
|
What is the use of Monolingual Corpora in SMT
|
|
2
|
1704
|
December 6, 2017
|
|
Training with out-of-domain data
|
|
0
|
1593
|
November 3, 2017
|
|
How is google's transformer translate between Chinese and English?
|
|
0
|
1734
|
November 1, 2017
|
|
Multiple translations open nmt
|
|
1
|
1453
|
October 31, 2017
|
|
Quality estimation / pred_score
|
|
3
|
1989
|
October 25, 2017
|
|
Paragraph vs sentence segmentation
|
|
2
|
2969
|
October 16, 2017
|
|
What is the best way to generate parallel corpus as per your past experience?
|
|
0
|
1422
|
September 26, 2017
|
|
In parallel corpus what should I keep, single sentence in each line or paragraph for MT?
|
|
2
|
1370
|
September 19, 2017
|
|
Metrics (Bleu, ppl, gold ppl, pred ....)
|
|
7
|
20744
|
September 14, 2017
|
|
About mask in attention layer and decoder
|
|
4
|
2511
|
September 12, 2017
|
|
How to create models that translate very quickly
|
|
7
|
3823
|
August 30, 2017
|
|
Exposure bias during training
|
|
3
|
2467
|
August 10, 2017
|
|
Improve BLEU by Coverage and Context Gate
|
|
6
|
2281
|
August 10, 2017
|
|
Use of Monolingual corpora in OPENNMT
|
|
7
|
3675
|
July 26, 2017
|
|
Using features for domain/client/subject adaptation
|
|
6
|
2482
|
July 12, 2017
|
|
Did someone test RNN with larger recurrence?
|
|
5
|
1497
|
June 23, 2017
|
|
Training chatbot with multiple inputs (to add context)
|
|
4
|
4774
|
June 22, 2017
|
|
Corpus compactization
|
|
2
|
1972
|
June 21, 2017
|
|
Incremental vocab
|
|
6
|
2047
|
June 21, 2017
|
|
Automatic training corpus filtering
|
|
15
|
4776
|
June 16, 2017
|
|
Implementing hashing to massively improve performance (by 95%)
|
|
0
|
1359
|
June 13, 2017
|
|
Speech-to-text using Convolutional LSTM layers
|
|
1
|
1516
|
June 8, 2017
|
|
Sentence length affect perplexity decrease
|
|
2
|
2617
|
June 2, 2017
|
|
Simple combination between SMT and NMT
|
|
0
|
1600
|
May 31, 2017
|
|
Alternative methods for <UNK> substitution
|
|
5
|
2874
|
May 29, 2017
|
|
Importance Sampling - training speed
|
|
1
|
1768
|
May 29, 2017
|
|
Weird Output after many attempts to train
|
|
0
|
1481
|
May 29, 2017
|