WorkStudy Spring 2006

Student: Arif Emre Caglar

Blog: Word Similarity

Schedule:

Week 1: (March 10)

1. Lexical semantics – Regina Barzilay, Lec 7

2. Learning similarity from corpora – Regina Barzilay, Lec 8

Reports: Lexical semantics, answers to questions

Week 2: (March 17)

1. WordNet

2. Probability Refresh Notes - http://ais.ku.edu.tr/course/8566/prob17.pdf

3. Statistical Learning Methods: http://aima.cs.berkeley.edu/newchap20.pdf - EM Algorithm

4. N-gram notes – Speech and Language Understanding – Chapter 4 – Ngrams

5. Introduction to Computational Linguistics – wk05

Reports: N-grams

Week 3: (March 24)

1. Chapters 2,3, 9 - Statistical Language Learning – Eugene Charniak

2. Word Vectors and Search Engines - infomap

3. Automatic Retrieval and Clustering of Similar Words – Dekang Lin, acl98

4. DomainTextStructure.pdf

5. Class-Based n-gram Models of Natural Language – Brown et. al.

6. Infomap and SRILM

7. Project Ideas due

Report: Vectors, DekangLin Summary, Charniak

Week 4:

1. Probabilistic Language Modeling – Regina Barzilay, Lec03.pdf

2. Infomap practice

3. TREC Conference Proceedings: check QA, terabyte, blog track publications.

4. Lexical Attraction Models of Language – Deniz Yuret, clpaper.ps

5. A Model of Lexical Attraction and Repulsion – Beeferman et. al.

6. Corpus linguistics – wikipedia

7. Hidden markov model – wikipedia

Report:

Week 5:

1. Chapter 2 - Manning and Schutze

2. A Variable-Length Category-Based N-Gram Language Model – Niesler and Woodland

3. Chapter 2 - Manning and

Report: