OpenNMT Forum

Research


Topic Replies Activity
About the Research category 1 December 23, 2016
OpenNMT torch vs OpenNMT-tf 5 June 12, 2019
Pytorch hub - BERT, GPT, Tacotron, WaveGlow, DCGAN, PGAN 1 June 10, 2019
Any idea about crowd sourcing translation? HELP! 3 June 8, 2019
Filter big monolingual corpus 4 June 6, 2019
Attention visualization for Image to Latex 2 June 3, 2019
Bleu score falling when detokenizing, detruecasing and de subword BPE 15 May 28, 2019
Fixed vs trainable embeddings 6 May 13, 2019
Arabic to English translation model 3 May 5, 2019
Does converting trained model from FP32 to FP16 improve inference performance? 3 April 30, 2019
Full hybrid MT with termino management 1 April 26, 2019
How to determine alignments accuracy? 1 April 5, 2019
How to split large paragraph into list of sentences? 2 April 11, 2019
Where can I find sota BLEU scores results for various language pairs? 3 April 11, 2019
Doc2vec and Transformer 7 April 4, 2019
Expanding the model to two-directional and/or Multi-Language Support 7 March 28, 2019
Star-transformer 1 March 11, 2019
Suggestion: reduce rivalry with a checksum 1 March 2, 2019
How to estimate number of iterations? 7 January 28, 2019
Has anyone experimented with the dense bridge? 3 January 8, 2019
How long to train a model without overfitting? 3 December 30, 2018
Low ressource languages, infinite training, and back-translation 4 December 8, 2018
What is the relationship between ppl, accuracy and bleu scores in machine translation? In my experiment, although ppl and accuracy on the validationset are greatly improved, Bleu scores is reduced 1 November 25, 2018
Questions on large batch size training with Transformer in low-resource scenario 3 November 19, 2018
Is there a paper to cite if OpenNMT is used in sequence mapping tasks other than neural machine translation? 2 November 16, 2018
Modifying the gradients during training 3 October 17, 2018
Looking for a master's thesis topic 6 October 9, 2018
Improvement of performance by data normalization 23 August 23, 2018
Using numerical data as input for Encoder 4 September 27, 2018
High Rank RNN model as Encoder or Decoder 2 September 26, 2018