fairly comprehensive notes for topics Michael Collins teachs in statistical NLP:
- Language models
- Hidden Markov models and tagging (sequence labeling) problems
- PCFGs
- Lexicalized PCFGs
- IBM Models 1 and 2 for machine translation
- Phrase-based translation models
- Log-linear models
- Log-linear models, MEMMs, and CRFs
- The forward-backward algorithm
- The EM algorithm
- The inside-outside algorithm
http://www.cs.columbia.edu/~mcollins/
0 Comments:
Post a Comment