CS 562/662: Natural Language Processing

Time: TR 2-3:30
Location: GH 5

Instructor: Kyle Gorman

Office hours: M 1-3 (and by request), GH 110

Natural language processing (NLP) is the engineering subfield of computational linguistics, the science of natural (i.e., human) language computation. This class covers algorithms and models which take language sequences (in this course, text) as input and produce useful structural annotations as output. Students in the course will implement core parts of NLP pipelines and evaluation tools.


80% MPs (10% each), 20% class participation


D. Jurafsky & J.H. Martin. 2008. Speech and language processing: An introduction to natural language processing, computational linguistics and speech recognition. 2nd edition. Upper Saddle River, NJ: Pearson Prentice Hall. (NB: The 1st edition differs considerably and chapter numbers will not match those used here.)


Whig history of NLP
Probability theory review
1/6 J&M, chap. 1
Winograd 1973
Slides [PDF]
Monologue [PDF]
Text encoding
1/8 Spolsky 2003
Gorman 2014
Slides [PDF]
Text normalization 1/13 Sproat et al. 2001 Slides [PDF]
Word similarity 1/15 J&M, chaps. 19-20
Mikolov et al. 2013
Slides [PDF]
Stemming and lemmatization
Latent semantic analysis
1/20 Bellegarda 2005
Blei 2012
Slides [PDF]
Notebook [ipynb]
Topic modeling
Linear classifiers for NLP
1/22 MP 1 due Slides [PDF]
Notebook [ipynb]
Document classification
Sentiment analysis
1/27 Pang et al. 2002 Slides [PDF]
Computational phonology
Computational morphology
1/29 J&M, chap. 11
Kaplan & Kay 1994
MP 2 due Slides [PDF]
Tagging and chunking 2/3 J&M, chaps. 5-6
Marcus et al. 1993
Collins 2002
Slides [PDF]
Computational syntax 2/5 MP 3 due Slides [PDF]
Computational semantics 2/10 J&M, chaps. 17-18.3
Context-free grammars
Tree & grammar transforms
2/12 J&M, chap. 16 MP 4 due Slides [PDF]
Constituency parsing I 2/17 J&M, chaps. 13-14 Slides [PDF]
Dependency parsing I 2/19 J&M, chap. 12
Zhang & Clark 2011
Handout [PDF]
Constituency parsing II 2/24 Bikel 2004
Klein & Manning 2003
MP 5 due Slides [PDF]
Dependency parsing II 2/26 MP 6 due
Machine translation I 3/3 J&M, chap. 25 Slides [PDF]
Handout [PDF]
Machine translation II 3/5 Chiang 2005 Slides [PDF]
Evaluation 3/10 Belz 2009
Resnik & Lin 2010
Biomedical applications 3/12 MP 7 due
3/19 MP 8 due

(Activity in the week of March 16th TBD)


Common acroynms

Students with disabilities

Our program is committed to all students achieving their potential. If you have a disability or think you may have a disability (physical, learning, hearing, vision, psychological) which may need a reasonable accommodation please contact Student Access at (503) 494-0082 or e-mail at orchards@ohsu.edu to discuss your needs. You can also find more information at http://www.ohsu.edu/student-access. Because accommodations can take time to implement, it is important to have this discussion as soon as possible. All information regarding a student's disability is kept in accordance with relevant state and federal laws.

Grade submission policy

Graduate Studies in the OHSU School of Medicine is committed to providing grades to students in a timely manner. Course instructors will provide students with information in writing at the beginning of each course that describes the grading policies and procedures including but not limited to evaluation criteria, expected time needed to grade individual student examinations and type of feedback they will provide. Class grades are due to the Registrar by the Friday following the week of finals.