|
|
Michael Collins Vikram S. Pandit Professor of Computer Science, Columbia University. Office: Room 723, Schapiro CESPR Email: mcollins [at] cs.columbia.[first 3 letters in "education"] Mailing Address: Columbia University Department of Computer Science 1214 Amsterdam Avenue M/C 0401 450 CS Building New York, NY 10027 |
-
Affiliations: Columbia
University, Google NYC.
-
Current teaching
(Spring
2020):
COMS W4705, Natural Language Processing.
-
Previous semester's teaching
(Fall
2018):
COMS W4705, Natural Language Processing,
(Spring
2019):
COMS W4705, Natural Language Processing.
-
Online teaching:
In Spring 2013 I taught an
online course on Natural Language Processing
on
Coursera.
Notes for the Coursera class are posted
here.
-
Publications
(for an up-to-date list see my profile on
Google scholar).
- Bio: My research interests are in natural language processing, and machine learning. I completed a PhD in computer science from the University of Pennsylvania in December 1998. From January 1999 to November 2002 I was a researcher at AT&T Labs-Research, and from January 2003 until December 2010 I was an assistant/associate professor at MIT. I joined Columbia University in January 2011. I am also a research scientist at Google NYC.
-
Students and Postdocs
-
Awards: NSF career award, Alfred P. Sloan research fellowship,
ACL fellow,
faculty finalist for
the 2012 Blavatnik
award. Best paper
awards at EMNLP 2002, EMNLP 2004, UAI 2004, UAI 2005, CoNLL 2008, EMNLP 2010. Test of time award at NAACL 2018.
-
I've been trying to make an effort to write up fairly
comprehensive notes for topics I teach in statistical NLP.
Most recently:
And also:
- 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
- MEMMs (Log-linear taggers)
- Log-linear models, MEMMs, and CRFs
- The forward-backward algorithm
- The EM algorithm
- The inside-outside algorithm
-
Previous teaching:
- Fall 2012: COMS W4705, Natural Language Processing.
- Spring 2012: COMS E6998, Machine learning for natural language processing
- Fall 2011: COMS W4705, Natural Language Processing.
- Spring 2011: COMS E6998-3, Machine learning for natural language processing
-
Software and Data Sets (including source code for
my PhD thesis parser).
- Past Teaching