A CNN-LSTM model with 2D positional encoding and BLEU-reward sequence-level training achieves state-of-the-art image-to-LaTeX translation on IM2LATEX-100K.
Minimum Risk Training for Neural Machine Translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to arbitrary evaluation metrics, which are not necessarily differentiable. Experiments show that our approach achieves significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system across various languages pairs. Transparent to architectures, our approach can be applied to more neural networks and potentially benefit more NLP tasks.
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training
A CNN-LSTM model with 2D positional encoding and BLEU-reward sequence-level training achieves state-of-the-art image-to-LaTeX translation on IM2LATEX-100K.