|
Using a pretrained summarization model on a new document
|
|
3
|
3022
|
March 11, 2017
|
|
Shuffle samples during training
|
|
7
|
2135
|
March 16, 2020
|
|
No <unk> token in the dataset but <unk> is generated in the end of all output sentences
|
|
3
|
3019
|
April 12, 2018
|
|
Using SharedEmbeddings Transformer model with Pretrained Embeddings
|
|
0
|
1071
|
February 8, 2024
|
|
Bi-directional language model
|
|
3
|
3007
|
April 10, 2018
|
|
Does continuing training start from unseen/less-seen data?
|
|
5
|
2452
|
February 22, 2021
|
|
Decreasing run time
|
|
2
|
1950
|
April 25, 2021
|
|
Using OpenNMT for Information Retrieval
|
|
3
|
1688
|
May 27, 2018
|
|
RuntimeError: Conv1D on CPU currently requires the oneDNN library (a.k.a. DNNL) which is not integrated in this build
|
|
5
|
2449
|
December 14, 2022
|
|
Automatic post-edit training of a training
|
|
5
|
2449
|
June 14, 2018
|
|
Worse performance with different CTranslate2 quantization types
|
|
2
|
3459
|
June 14, 2023
|
|
AI Grant announcement
|
|
1
|
2382
|
July 27, 2017
|
|
IndexError: list index out of range error
|
|
2
|
3458
|
November 7, 2019
|
|
Using learning_rate option with Noam decay scheme
|
|
1
|
4235
|
March 4, 2019
|
|
Weight table:set weight of some vocabulary
|
|
5
|
2445
|
May 15, 2017
|
|
Re-training Existing Model with Monolingual Corpora
|
|
7
|
2110
|
August 29, 2018
|
|
Words are lost when transforme long sentences
|
|
5
|
2432
|
October 22, 2020
|
|
ONMT net structure?
|
|
5
|
2431
|
May 11, 2018
|
|
Sentence piece in OpenNMT-py
|
|
3
|
2970
|
June 28, 2019
|
|
Large perplexity
|
|
6
|
2238
|
December 12, 2018
|
|
Training crash at validation
|
|
4
|
2649
|
July 1, 2021
|
|
Difference between bpe and character-level tokenization for BLUE score
|
|
2
|
3415
|
December 15, 2019
|
|
Transformer OpenNMT-py standard hyperparameters + pretrained model
|
|
4
|
2632
|
February 14, 2019
|
|
OpenNMT-py doubts
|
|
5
|
2401
|
January 1, 2018
|
|
Indigenous languages: first try with Palikúr - looking for advices
|
|
2
|
1071
|
April 21, 2019
|
|
About mask in attention layer and decoder
|
|
4
|
2620
|
September 12, 2017
|
|
Predictive translation server
|
|
4
|
2618
|
August 29, 2017
|
|
Is it normal to see "Weighted corpora loaded so far" in a loop during the finetuning phase on a very small dataset?
|
|
6
|
2206
|
February 15, 2024
|
|
BPE and other tokenization options with rest_translation_server.lua
|
|
5
|
2376
|
January 2, 2018
|
|
AttributeError: 'SequenceRecordInputter' object has no attribute 'input_depth'
|
|
5
|
2375
|
March 22, 2019
|
|
OpenNMT translate string as an input
|
|
4
|
2596
|
October 12, 2018
|
|
MS Azure image?
|
|
1
|
1291
|
March 9, 2017
|
|
Tokenizer v1.20.0 with SentencePiece v0.1.92 potentially problematic?
|
|
5
|
2357
|
October 3, 2020
|
|
Linker error when compiling CTranslate2 with "-march=corei7-avx" (CXX_FLAGS)
|
|
6
|
2182
|
September 12, 2020
|
|
Wrong word UNK replacement
|
|
7
|
2041
|
October 15, 2019
|
|
OpenNMT-tf Fine tuning base model gives worse and decreases BLEU scores
|
|
8
|
1923
|
December 5, 2018
|
|
Multimodal feature input for seq2seq
|
|
7
|
2038
|
August 11, 2021
|
|
Error whey saving vocab file in openmt-py
|
|
1
|
1286
|
January 25, 2021
|
|
Raising training speed without comprimising too much on quality
|
|
7
|
2027
|
December 4, 2017
|
|
OpenNMT-py installation in Google Colab
|
|
2
|
3302
|
April 30, 2020
|
|
Improving the gpuid option
|
|
4
|
2550
|
January 18, 2017
|
|
Error with latest CTranslate2 version in OpenNMT-py REST server
|
|
3
|
2848
|
July 5, 2021
|
|
The difference between parameter
|
|
8
|
1898
|
January 4, 2017
|
|
Could I submit pull request to tokenization hook for Korean and Japanese?
|
|
3
|
1598
|
May 23, 2018
|
|
What's wrong with my train.py?
|
|
5
|
2320
|
December 20, 2017
|
|
-fix_word_vecs_enc and -fix_word_vecs_dec not doing what I expect them to do
|
|
7
|
2007
|
September 16, 2019
|
|
How to coordinate GPU memory usage
|
|
5
|
2316
|
November 20, 2017
|
|
How long to train a model without overfitting?
|
|
2
|
3275
|
December 30, 2018
|
|
About input_feed
|
|
6
|
2142
|
July 14, 2017
|
|
How should I clean the texts before training?
|
|
4
|
2535
|
February 11, 2020
|