|
Minimum Sentences for Languages Model
|
|
1
|
441
|
May 18, 2021
|
|
How to use Bert embedding into OpenNMT seq2seq model
|
|
4
|
1112
|
May 11, 2021
|
|
State of the art in Machine Translation (2021)
|
|
4
|
2335
|
May 7, 2021
|
|
Multilingual Parallel Corpus
|
|
5
|
488
|
April 16, 2021
|
|
Extracting and injecting attention weights
|
|
2
|
638
|
March 30, 2021
|
|
Length and Coverage Normalization - Deciding on parameters
|
|
1
|
345
|
March 24, 2021
|
|
What algorithm does Open-NMT-py use?
|
|
2
|
617
|
March 24, 2021
|
|
How to compare two testsets
|
|
1
|
295
|
March 16, 2021
|
|
Best checkpoint selection for NMT
|
|
11
|
1486
|
March 12, 2021
|
|
CTranslate2's target prefix
|
|
10
|
644
|
March 4, 2021
|
|
Similarity of the fine-tuning data with domain for successful adaptation
|
|
0
|
411
|
February 9, 2021
|
|
Quantization for training
|
|
3
|
367
|
February 5, 2021
|
|
Suggested value for length_penalty
|
|
1
|
458
|
December 30, 2020
|
|
Calculate TER metrics instead of using 'Levenshtein_distance'
|
|
1
|
1096
|
December 3, 2020
|
|
Paragraph-based training with LSTM Network
|
|
0
|
388
|
November 14, 2020
|
|
Has anyone trained transformer on the multi30k dataset?
|
|
3
|
660
|
November 9, 2020
|
|
Multimodal: initialize hidden state of encoder + transformer
|
|
0
|
464
|
November 2, 2020
|
|
Tokenization: separator on suffix or prefix
|
|
6
|
677
|
October 2, 2020
|
|
Training back-translation model separately
|
|
0
|
428
|
October 1, 2020
|
|
Batched seq2seq in RNNs
|
|
6
|
619
|
September 9, 2020
|
|
Training Transformer on small dataset of source code sequences
|
|
1
|
677
|
September 8, 2020
|
|
SentencePiece: Understanding pre-tokenization on raw Unicode bytes?
|
|
2
|
922
|
August 26, 2020
|
|
Language Model Accuracy
|
|
1
|
558
|
August 21, 2020
|
|
OpenNMT with CTranslate2: the most efficient NMT system at WNGT 2020
|
|
1
|
1349
|
July 28, 2020
|
|
Should you scale step-based parameters with the number of devices you use?
|
|
2
|
481
|
July 27, 2020
|
|
Translate from multiple paragraphs to sentence
|
|
2
|
361
|
July 16, 2020
|
|
Multilingual training experiments
|
|
7
|
1846
|
June 25, 2020
|
|
Doubt with overview of NMT Pipeline
|
|
4
|
739
|
June 16, 2020
|
|
Cleaning and Normalizing WMT Dataset for French to English
|
|
0
|
603
|
June 16, 2020
|
|
BPE vs Word tokenization for Preprocessing
|
|
1
|
1164
|
June 15, 2020
|