|
Batched seq2seq in RNNs
|
|
6
|
1231
|
September 9, 2020
|
|
Training Transformer on small dataset of source code sequences
|
|
1
|
1401
|
September 8, 2020
|
|
SentencePiece: Understanding pre-tokenization on raw Unicode bytes?
|
|
2
|
1804
|
August 26, 2020
|
|
Language Model Accuracy
|
|
1
|
1222
|
August 21, 2020
|
|
OpenNMT with CTranslate2: the most efficient NMT system at WNGT 2020
|
|
1
|
1942
|
July 28, 2020
|
|
Should you scale step-based parameters with the number of devices you use?
|
|
2
|
1115
|
July 27, 2020
|
|
Translate from multiple paragraphs to sentence
|
|
2
|
736
|
July 16, 2020
|
|
Doubt with overview of NMT Pipeline
|
|
4
|
1432
|
June 16, 2020
|
|
Cleaning and Normalizing WMT Dataset for French to English
|
|
0
|
1174
|
June 16, 2020
|
|
BPE vs Word tokenization for Preprocessing
|
|
1
|
2351
|
June 15, 2020
|
|
How can I get some hidden states of model(such as self-attention matrix) during translation
|
|
3
|
1099
|
June 10, 2020
|
|
Are you interested in training Russian-Abkhazian parallel corpus?
|
|
29
|
4664
|
June 9, 2020
|
|
Length Penalty Question
|
|
5
|
3650
|
June 2, 2020
|
|
Model "jamming" on words
|
|
2
|
759
|
May 18, 2020
|
|
Sentence meaning score
|
|
1
|
755
|
May 18, 2020
|
|
Effectiveness of Transformer model on small dataset
|
|
7
|
6847
|
May 12, 2020
|
|
Doubt with Number of Epoch
|
|
1
|
974
|
May 11, 2020
|
|
Transformers on low resource corpora
|
|
5
|
2662
|
May 4, 2020
|
|
Bad data in WMT14 en-de
|
|
1
|
747
|
April 23, 2020
|
|
Are composite tokens possible?
|
|
1
|
786
|
April 17, 2020
|
|
Which BLEU script to use?
|
|
1
|
2452
|
April 17, 2020
|
|
What's the best en-de WMT14 BLEU in onmt?
|
|
1
|
725
|
April 9, 2020
|
|
Multifeature translation question
|
|
18
|
2474
|
March 30, 2020
|
|
Quality/Confidence score
|
|
0
|
842
|
March 11, 2020
|
|
Qs about NMT learning
|
|
7
|
860
|
March 6, 2020
|
|
Looking for a master's thesis topic
|
|
6
|
2656
|
March 4, 2020
|
|
In a Transformer model, why does one sum positional encoding to the embedding rather than concatenate it?
|
|
2
|
2961
|
February 17, 2020
|
|
CCMatrix: A billion-scale bitext data set for training translation models
|
|
2
|
1431
|
February 12, 2020
|
|
Trainings steps Q
|
|
1
|
730
|
February 10, 2020
|
|
Types of generalizations learned by NMT?
|
|
0
|
734
|
February 10, 2020
|