|
Sharing word embeddings, the wrong way—curious about what happened
|
|
2
|
1498
|
May 12, 2021
|
|
Pretrained word embeddings for only one of multiple inputs
|
|
1
|
1830
|
June 17, 2020
|
|
Modifying the gradients during training
|
|
2
|
1493
|
October 17, 2018
|
|
Best approach for in-domain adaptation
|
|
3
|
1293
|
April 20, 2019
|
|
Evalution error
|
|
1
|
1827
|
August 30, 2022
|
|
Test data from different corpus
|
|
4
|
1155
|
March 18, 2019
|
|
Dynamic dataset: uniform sampling and continue training
|
|
2
|
1487
|
April 24, 2018
|
|
Differentiable memory
|
|
1
|
1819
|
December 26, 2016
|
|
Any scripts to start multi-nodes training?
|
|
4
|
1149
|
September 29, 2022
|
|
Any negative effects of using the parameter "Replace unknowns = True" in inference?
|
|
3
|
1281
|
August 31, 2023
|
|
Possible to use transformer architecture to do what gpt2 does?
|
|
1
|
1810
|
January 20, 2020
|
|
High Rank RNN model as Encoder or Decoder
|
|
1
|
1810
|
September 26, 2018
|
|
Alternative words
|
|
2
|
1477
|
December 11, 2017
|
|
Multi-Blue.perl(why Blue score is greater than one )
|
|
2
|
1478
|
May 24, 2020
|
|
Error in converting Fairseq Wikitext-103 transformer_lm model
|
|
1
|
1808
|
March 26, 2024
|
|
OpenNMT : lua code debug
|
|
1
|
1808
|
October 24, 2017
|
|
Nothing in vocab.pt after preprocessing
|
|
1
|
1811
|
April 25, 2018
|
|
How to get flatten parameters, gradient of Encoder & Decoder? (Encoder:getParameters() work?)
|
|
1
|
1805
|
March 14, 2017
|
|
Train Transformer model on Google Colab
|
|
1
|
1802
|
May 6, 2019
|
|
Language Model Accuracy
|
|
1
|
1802
|
August 21, 2020
|
|
Better bleu score when warmup_steps greater than train_steps
|
|
1
|
1800
|
September 28, 2021
|
|
Two-to-one translation - combined or seperate models?
|
|
1
|
1804
|
April 23, 2025
|
|
How to use multi-GPU parallel training with an old commit on Feb 23
|
|
1
|
1798
|
July 25, 2017
|
|
Error in Chinese Abstractive summarization preprocessing
|
|
2
|
1467
|
May 28, 2021
|
|
How to incorporate subwords in the configuration
|
|
1
|
1796
|
October 21, 2021
|
|
Question about the implementation of copy mechanism
|
|
1
|
1795
|
August 1, 2018
|
|
Onmt with multiple features
|
|
2
|
1465
|
December 14, 2019
|
|
Translation API Not Working
|
|
1
|
1792
|
May 30, 2024
|
|
Port OpenNMT-py models to HuggingFace
|
|
1
|
1790
|
June 24, 2021
|
|
Typo in FAQ OpenNMTTokenizer
|
|
2
|
1455
|
October 22, 2020
|
|
Validation dataset
|
|
2
|
1453
|
May 28, 2020
|
|
Phrase tables and <unk> replace
|
|
2
|
1454
|
October 8, 2018
|
|
Poor test set Accuracy
|
|
2
|
1452
|
November 26, 2020
|
|
How do you correct?
|
|
1
|
1776
|
December 2, 2019
|
|
How to change the data parallelism to model parallelsim?
|
|
2
|
1452
|
November 19, 2018
|
|
HDFS support in OpenNMT-tf
|
|
1
|
1774
|
April 13, 2018
|
|
How to add image features in onmt-py
|
|
2
|
1445
|
March 29, 2020
|
|
Low accuracy of chinese-English model
|
|
1
|
1770
|
June 18, 2020
|
|
Multi-source vocabularies
|
|
2
|
1444
|
July 9, 2021
|
|
Multiple translations open nmt
|
|
1
|
1768
|
October 31, 2017
|
|
Unable to find the final model
|
|
2
|
1442
|
September 14, 2017
|
|
Running translate on Quickstart demo .pt
|
|
2
|
1440
|
December 4, 2019
|
|
Inferences from non-training data all giving the same result in OpenNMT-tf
|
|
2
|
1439
|
September 15, 2018
|
|
How to specify input data files for ParallelInputter?
|
|
2
|
1435
|
December 18, 2018
|
|
Opennmt-tf not recognizing GPU
|
|
3
|
1239
|
April 4, 2022
|
|
How should I adjust the parameters
|
|
2
|
1428
|
October 26, 2022
|
|
Can I change the batch_size when trainning in the next epoch?
|
|
2
|
1428
|
September 21, 2019
|
|
The following problems occur in the preprocessing of Chinese-English translation
|
|
2
|
1427
|
June 29, 2020
|
|
Running two models at the same run
|
|
3
|
1233
|
December 3, 2020
|
|
Transformer model error
|
|
1
|
1742
|
December 24, 2018
|