Dexa
/
NLP Highlights
Learn more
Follow
Practical NLP Tips
Myle suggests a smart mix of online and offline generation for better results. Sergey emphasizes the importance of testing loss functions, recommending overfitting a small subset of the training set to ensure desired outcomes.
Add to Radar
Share
In this clip
Sergey Edunov
Myle Ott
Pradeep Dasigi
From this podcast
NLP Highlights
53 - Classical Structured Prediction Losses for Sequence to Sequence Learning, with Sergey and Myle
Related Questions
What are some techniques for training machine learning models?
Give me tips on deep learning