|
Deep transformer with more layers
|
|
2
|
1309
|
August 24, 2021
|
|
Suggestions for translating XML
|
|
9
|
3717
|
August 1, 2021
|
|
Implementing Boosting Techniques
|
|
9
|
1743
|
July 28, 2021
|
|
H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences
|
|
0
|
1177
|
July 27, 2021
|
|
Multi-source vocabularies
|
|
2
|
1108
|
July 9, 2021
|
|
Best practices for multiple corpora
|
|
0
|
920
|
July 9, 2021
|
|
Size of subwords vocabulary?
|
|
3
|
3529
|
July 7, 2021
|
|
Linguee Open Source?
|
|
2
|
1232
|
June 30, 2021
|
|
How Much Does Tokenization Affect Neural Machine Translation?
|
|
1
|
2389
|
June 21, 2021
|
|
TLIte Converter
|
|
4
|
1362
|
June 8, 2021
|
|
Training convergence and beam size impact
|
|
5
|
2786
|
June 2, 2021
|
|
Minimum Sentences for Languages Model
|
|
1
|
1275
|
May 18, 2021
|
|
How to use Bert embedding into OpenNMT seq2seq model
|
|
4
|
2355
|
May 11, 2021
|
|
State of the art in Machine Translation (2021)
|
|
4
|
4096
|
May 7, 2021
|
|
Multilingual Parallel Corpus
|
|
5
|
1060
|
April 16, 2021
|
|
Extracting and injecting attention weights
|
|
2
|
1412
|
March 30, 2021
|
|
Length and Coverage Normalization - Deciding on parameters
|
|
1
|
975
|
March 24, 2021
|
|
What algorithm does Open-NMT-py use?
|
|
2
|
1770
|
March 24, 2021
|
|
How to compare two testsets
|
|
1
|
816
|
March 16, 2021
|
|
Best checkpoint selection for NMT
|
|
11
|
3480
|
March 12, 2021
|
|
CTranslate2's target prefix
|
|
10
|
2199
|
March 4, 2021
|
|
Similarity of the fine-tuning data with domain for successful adaptation
|
|
0
|
928
|
February 9, 2021
|
|
Quantization for training
|
|
3
|
1058
|
February 5, 2021
|
|
Suggested value for length_penalty
|
|
1
|
2011
|
December 30, 2020
|
|
Calculate TER metrics instead of using 'Levenshtein_distance'
|
|
1
|
2571
|
December 3, 2020
|
|
Paragraph-based training with LSTM Network
|
|
0
|
921
|
November 14, 2020
|
|
Has anyone trained transformer on the multi30k dataset?
|
|
3
|
1618
|
November 9, 2020
|
|
Multimodal: initialize hidden state of encoder + transformer
|
|
0
|
1166
|
November 2, 2020
|
|
Tokenization: separator on suffix or prefix
|
|
6
|
2449
|
October 2, 2020
|
|
Training back-translation model separately
|
|
0
|
969
|
October 1, 2020
|