Sign in
Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora.
Gaurav Kumar
Philipp Koehn
Sanjeev Khudanpur
Published in:
CoRR (2021)
Keyphrases
</>
denoising
reinforcement learning
feature weights
active learning
supervised learning
learning algorithm
training data
machine learning
feature extraction
similarity measure
objective function