Difference between revisions of "Class Meeting for 10-710 09-06-2011"
From Cohen Courses
Jump to navigationJump to search| Line 21: | Line 21: | ||
* Max ent for NLP: [http://acl.ldc.upenn.edu/J/J96/J96-1002.pdf Berger et al., 1996, "A Maximum Entropy Approach to Natural Language Processing"] | * Max ent for NLP: [http://acl.ldc.upenn.edu/J/J96/J96-1002.pdf Berger et al., 1996, "A Maximum Entropy Approach to Natural Language Processing"] | ||
* Max ent for NLP: [http://acl.ldc.upenn.edu/W/W96/W96-0213.pdf Ratnaparkhi, 1996, "A Maximum Entropy Model for Part-of-Speech Tagging"] | * Max ent for NLP: [http://acl.ldc.upenn.edu/W/W96/W96-0213.pdf Ratnaparkhi, 1996, "A Maximum Entropy Model for Part-of-Speech Tagging"] | ||
| − | * Max ent for language modeling: [http://acl.ldc.upenn.edu/H/H93/H93-1021.pdf Lau et al., 1993, "Adaptive Language Modeling Using the Maximum Entropy Principle"] | + | * Max ent for language modeling: [http://acl.ldc.upenn.edu/H/H93/H93-1021.pdf Lau et al., 1993, "Adaptive Language Modeling Using the Maximum Entropy Principle"] ([[Paper::Lau et al HLT 1993| Wiki]]) |
Revision as of 00:19, 28 September 2011
This is one of the class meetings on the schedule for the course Structured Prediction 10-710 in Fall 2011.
HMMs, MaxEnt Taggers, and MEMMs
Required Readings
No additional readings from Thursday, but I will focus on this paper:
The Borthwick et al paper I discussed last Thursday is
Background Readings
- LSP: section 3.4 and appendix D through D.2. To understand why these models are often called "max ent," read appendix C.
- Max ent for NLP: Berger et al., 1996, "A Maximum Entropy Approach to Natural Language Processing"
- Max ent for NLP: Ratnaparkhi, 1996, "A Maximum Entropy Model for Part-of-Speech Tagging"
- Max ent for language modeling: Lau et al., 1993, "Adaptive Language Modeling Using the Maximum Entropy Principle" (Wiki)
