Scatterplot of KN/PYP language model results
Read OriginalThe article analyzes a scatterplot of language model perplexity results from Yee Whye Teh's research, comparing Interpolated Kneser-Ney (IKN), Modified Kneser-Ney (MKN), Hierarchical Dirichlet (HDLM), and Hierarchical Pitman-Yor (HPYLM) models. It discusses the theoretical similarity between KN and HPYLM models, notes the superior performance of MKN and HPYLM over IKN, and explains why HDLM performs worse, especially with longer contexts.
Comments
No comments yet
Be the first to share your thoughts!
Browser Extension
Get instant access to AllDevBlogs from your browser
Top of the Week
1
Quoting Thariq Shihipar
Simon Willison
•
2 votes
2
Using Browser Apis In React Practical Guide
Jivbcoop
•
2 votes
3
Better react-hook-form Smart Form Components
Maarten Hus
•
2 votes
4
Top picks — 2026 January
Paweł Grzybek
•
1 votes
5
In Praise of –dry-run
Henrik Warne
•
1 votes
6
Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On
Ferenc Huszár
•
1 votes
7
Vibe coding your first iOS app
William Denniss
•
1 votes
8
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook
•
1 votes
9
Dew Drop – January 15, 2026 (#4583)
Alvin Ashcraft
•
1 votes