Episode 16 - Evaluation of language models
Data Science et al.
English - January 10, 2020 09:00 - 30 seconds - 386 KB - ★★★★★ - 1 ratingTechnology Education machine learning nlp python data science analytics deep learning reinforcement learning cnn tensorflow encoder Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Previous Episode: Episode 15 - Basics of NLP
Next Episode: Episode 17 - Zero Shot Learning
Extrinsic evaluation
• Is the evaluation on a real task
• Can be slow to compute performance
Whereas Intrinsic evaluation
• Is the evaluation on a specific, intermediate task
• Fast to compute performance
• Helps understand subsystem