Difference between revisions of "Class Meeting for 10-710 09-01-2011"
From Cohen Courses
Jump to navigationJump to search (Created page with 'This is one of the class meetings on the schedule for the course Structured Prediction 10-710 in Fall 2011. === Hi…') |
|||
(7 intermediate revisions by 3 users not shown) | |||
Line 1: | Line 1: | ||
This is one of the class meetings on the [[Syllabus for Structured Prediction 10-710 in Fall 2011|schedule]] for the course [[Structured Prediction 10-710 in Fall 2011]]. | This is one of the class meetings on the [[Syllabus for Structured Prediction 10-710 in Fall 2011|schedule]] for the course [[Structured Prediction 10-710 in Fall 2011]]. | ||
− | === Hidden | + | === Hidden Markov Models as Structured Prediction === |
− | * [http://www.cs.cmu.edu/~wcohen/10- | + | * [http://www.cs.cmu.edu/~wcohen/10-710/09-01-hmms.ppt Slides in Powerpoint] |
+ | * [http://www.cs.cmu.edu/~wcohen/10-710/09-01-hmms.pdf Slides in PDF] | ||
=== Required Readings === | === Required Readings === | ||
Line 12: | Line 13: | ||
=== Optional Readings === | === Optional Readings === | ||
− | * [http://www.cs.cmu.edu/~wcohen/10-707/papers/bikel.pdf An Algorithm that Learns What's in a Name, Bikel ''et al'', MLJ 1999]. Another well-engineered and influential HMM-based NER system. | + | * [http://www.cs.cmu.edu/~wcohen/10-707/papers/bikel.pdf An Algorithm that Learns What's in a Name, Bikel ''et al'', MLJ 1999]. ([[Paper::Bikel et al MLJ 1999|Wiki]]) Another well-engineered and influential HMM-based NER system. |
* [http://www.stanford.edu/~grenager/papers/unsupie_final.ps Unsupervised Learning of Field Segmentation Models for Information Extraction, Grenager, Klein, and Manning, ACL 2005]. Unsupervised segmentation paper. | * [http://www.stanford.edu/~grenager/papers/unsupie_final.ps Unsupervised Learning of Field Segmentation Models for Information Extraction, Grenager, Klein, and Manning, ACL 2005]. Unsupervised segmentation paper. | ||
* [http://www-nlp.stanford.edu/~manning/papers/conll-ner.pdf Named Entity Recognition with Character-Level Models, Klein ''et al'', CoNLL 2003]. Interesting twist on the standard approach of token-tagging - NER by tagging characters and character n-grams. | * [http://www-nlp.stanford.edu/~manning/papers/conll-ner.pdf Named Entity Recognition with Character-Level Models, Klein ''et al'', CoNLL 2003]. Interesting twist on the standard approach of token-tagging - NER by tagging characters and character n-grams. | ||
Line 18: | Line 19: | ||
=== Background Readings === | === Background Readings === | ||
+ | * [http://www.morganclaypool.com/doi/abs/10.2200/S00361ED1V01Y201105HLT013 <i>LSP</i>]: chapter 1 (through 1.3) and section 3.3 (through 3.3.3); for some background on dynamic programming (buildup to Viterbi algorithm), see 2.3 (through 2.3.1, beyond if you're interested) | ||
* [http://acl.ldc.upenn.edu/W/W96/W96-0213.pdf A Maximum Entropy Part-Of-Speech Tagger, Ratnaparkhi, Workshop on Very Large Corpora 1996] | * [http://acl.ldc.upenn.edu/W/W96/W96-0213.pdf A Maximum Entropy Part-Of-Speech Tagger, Ratnaparkhi, Workshop on Very Large Corpora 1996] | ||
− | |||
− | |||
* [http://www.ai.mit.edu/people/mcollins/papers/tutorial_colt.pdf Mike Collins on learning in NLP], including a section on maxent taggers. | * [http://www.ai.mit.edu/people/mcollins/papers/tutorial_colt.pdf Mike Collins on learning in NLP], including a section on maxent taggers. | ||
* [http://www-diglib.stanford.edu/~klein/maxent-tutorial-slides-6.pdf Dan Klein on maxent]. | * [http://www-diglib.stanford.edu/~klein/maxent-tutorial-slides-6.pdf Dan Klein on maxent]. | ||
+ | * [http://lingpipe.files.wordpress.com/2008/04/lazysgdregression.pdf Bob Carpenter on maxent and SGD] has detailed derivations of multiclass logistic regression and its gradients. |
Latest revision as of 00:17, 28 September 2011
This is one of the class meetings on the schedule for the course Structured Prediction 10-710 in Fall 2011.
Contents
Hidden Markov Models as Structured Prediction
Required Readings
- Borkar 2001 Automatic Segmentation of Text Into Structured Records
- Frietag 2000 Maximum Entropy Markov Models for Information Extraction and Segmentation
Optional Readings
- An Algorithm that Learns What's in a Name, Bikel et al, MLJ 1999. (Wiki) Another well-engineered and influential HMM-based NER system.
- Unsupervised Learning of Field Segmentation Models for Information Extraction, Grenager, Klein, and Manning, ACL 2005. Unsupervised segmentation paper.
- Named Entity Recognition with Character-Level Models, Klein et al, CoNLL 2003. Interesting twist on the standard approach of token-tagging - NER by tagging characters and character n-grams.
Background Readings
- LSP: chapter 1 (through 1.3) and section 3.3 (through 3.3.3); for some background on dynamic programming (buildup to Viterbi algorithm), see 2.3 (through 2.3.1, beyond if you're interested)
- A Maximum Entropy Part-Of-Speech Tagger, Ratnaparkhi, Workshop on Very Large Corpora 1996
- Mike Collins on learning in NLP, including a section on maxent taggers.
- Dan Klein on maxent.
- Bob Carpenter on maxent and SGD has detailed derivations of multiclass logistic regression and its gradients.