|
Fine-tuning mBART
|
|
5
|
1724
|
July 3, 2022
|
|
Best way to custom model for every one
|
|
4
|
510
|
June 15, 2022
|
|
Mixture-of-Experts with Expert Choice Routing
|
|
1
|
612
|
June 5, 2022
|
|
OpenNMT and WMT21 Similar Language Task for the Spanish-Catalan and Spanish-Portuguese Language Pair
|
|
0
|
388
|
April 26, 2022
|
|
About onmt.utils.loss
|
|
1
|
453
|
April 23, 2022
|
|
Grammar Correction with OpenNMT
|
|
1
|
522
|
April 11, 2022
|
|
Transformer Parameters for Low-Resource Machine Translation
|
|
0
|
840
|
March 21, 2022
|
|
Some Basic Queries
|
|
2
|
577
|
February 28, 2022
|
|
Respect the format of a text
|
|
16
|
14052
|
February 13, 2022
|
|
Sentence Boundary Detection for Non-European languages
|
|
5
|
914
|
February 13, 2022
|
|
Build a Glossary
|
|
9
|
617
|
January 31, 2022
|
|
Train/Infer on paragraphs
|
|
15
|
1071
|
January 13, 2022
|
|
Retraining model with new datasets
|
|
2
|
483
|
January 6, 2022
|
|
Can better desubwording be done?
|
|
7
|
738
|
December 18, 2021
|
|
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
|
|
0
|
336
|
December 14, 2021
|
|
Compare BLEU score between models
|
|
2
|
367
|
December 13, 2021
|
|
End and Start Tokens
|
|
11
|
1528
|
November 29, 2021
|
|
Handling single word 1 to many translation
|
|
2
|
512
|
November 6, 2021
|
|
Efficiently Modeling Long Sequences with Structured State Spaces
|
|
0
|
452
|
October 6, 2021
|
|
YouTokenToMe - Up to 90x faster subword encoding
|
|
0
|
486
|
October 3, 2021
|
|
How an optimal parallel corpus should look like?
|
|
8
|
635
|
September 29, 2021
|
|
How to choose a best voc size?
|
|
14
|
4180
|
September 18, 2021
|
|
Fastformer: Additive Attention is All You Need
|
|
2
|
751
|
August 31, 2021
|
|
Single character tokenization?
|
|
10
|
3735
|
August 26, 2021
|
|
Using custom tags for domain adaptation
|
|
4
|
981
|
August 25, 2021
|
|
Deep transformer with more layers
|
|
2
|
548
|
August 24, 2021
|
|
Suggestions for translating XML
|
|
9
|
2103
|
August 1, 2021
|
|
Implementing Boosting Techniques
|
|
9
|
733
|
July 28, 2021
|
|
H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences
|
|
0
|
427
|
July 27, 2021
|
|
Multi-source vocabularies
|
|
2
|
517
|
July 9, 2021
|