Linguistics 473
Computational Linguistics Fundamentals
Summer 2012
Computational Linguistics Fundamentals
Course Information
This course examines computer applications in the automatic processing of natural language. Students will develop and reinforce foundational skills in the fields of linguistics, probability, statistics, and computer science, as preparation for further study in computational linguistics.
Topics may include:
- basic Unix: pipes, regex, issuing cluster batch jobs
- formal grammars
- finite-state automata and transducers
- reading the literature: ∑, ∏, argmax, evaluation, precision, recall
- random variables, independence, expected value
- probability distributions, joint and conditional probabilities, Bayes' thoerem
- data structures and algorithms for text-processing, Unicode
- overview of current research sub-specialties in the field
Ling473 is required for the following students:
- students who need to review these critical skill areas prior to entering the Professional Master's in Computational Linguistics (CLMA) program;
- CLMA students who completed the prerequisites for Ling570 but need additional practice with natural language processing techniques; and
- students in the Natural Language Technology (NLT) certificate program.
Class Time & Location
Tuesdays and Thursdays 4:30-6:20 p.m.First Class: Thursday, July 19, 2012
Last Class: Thursday, September 6, 2012
Location: Loew 105, or online via AdobeConnect
Credits: 3
Distance Learning
This course is available in a fully-online format. Students have the option to attend class in-person, live-online, or recorded-offline—or by any combination of these. The URL for the online classroom is http://uweoconnect.extn.washington.edu/r44411238/.Instructor
 |
Glenn Slayden gslayden@u.washington.edu Skype: glenn.slayden |
Office Hours
I am available to meet with students after class. Additional office hours are via Skype, by appointment.Prerequsites
- CSE 326 (Data Structures)
- STAT 391 (Probability and Statistics for Computer Science)
- Ability to program in a programming language that is available on the the UW Computational Linguistics Cluster, such as:
- C
- C++
- C# (Mono)
- Java
- Python
- Perl
Waiver of these prerequisites must be approved by supervising professor Fei Xia.
Textbooks
There are no required texts. The following textbooks are strongly recommended and are required for NLT/CLMA students when they take Ling570:- Charles Grinstead and J. Laurie Snell Introduction to Probability
- Daniel Jurafsky and James H. Martin. (2008) Speech and Language Processing (2nd edition). New Jersey: Prentice-Hall.
- Christopher D. Manning and Hinrich Schütze. (1999) Foundations of Statistical Natural Language Processing. Cambridge: MIT Press.