REVIEW 3 cited by
Minimum Risk Training for Neural Machine Translation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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.
Forward citations
Cited by 3 Pith papers
-
Neural Text Generation with Unlikelihood Training
Training neural language models with an unlikelihood objective that penalizes repeated and frequent tokens reduces degenerate, repetitive text while preserving quality.
-
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.
-
An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation
DAgger-style imitation learning outperforms REINFORCE reinforcement learning for paraphrase generation with a pointer-generator, and the best model reaches state-of-the-art scores on Quora.
Discussion (0). Continue with ORCID to comment.