CS 288: Statistical Natural Language Processing

CS 288: Statistical Natural Language Processing

CS 288: Statistical Natural Language Processing, Spring 2010
Instructor: Dan Klein Lecture: Monday and Wednesday, 2:30pm-4:00pm, 405 Soda Hall Office Hours: Monday 4pm-5pm and Thursday 2:30pm-3:30pm in 724 (or 730) Sutardja Dai Hall.

Announcements

1/19/10:  The course newsgroup is ucb.class.cs288. If you use it, I'll use it!
1/19/10:  The previous website has been archived.
1/19/10:  Assignment 1 is posted.
2/2/10:  Assignment 2 is posted.
2/18/10:  Assignment 3 is posted.
3/5/10:  Comments on writeups posted.
3/7/10:  Assignment 4 is posted.
4/4/10:  Final project guidelines are posted.
4/4/10:  Assignment 5 is posted.
4/12/10:  There are extra office hours on 4/12 (4-6pm) and 4/15 (2:30-4:00pm).

Description

This course will explore current statistical techniques for the automatic analysis of natural (human) language data. The dominant modeling paradigm is corpus-driven statistical learning, with a split focus between supervised and unsupervised methods.

In the first part of the course, we will examine the core tasks in natural language processing, including language modeling, syntactic analysis, semantic interpretation, coreference resolution, and discourse analysis. In each case, we will discuss the underlying linguistic phenomena, which features are relevant to the task, how to design efficient models which can accommodate those features, and how to learn such models.  In the second part of the course, we will explore how these core techniques can be applied to user applications such as information extraction, question answering, speech recognition, machine translation, and interactive dialog systems.

Course assignments will highlight several core NLP tasks and methods. For each task, you will construct a basic system, then improve it through a cycle of linguistic error analysis and model redesign. There will also be a final project, which will investigate a single topic or application in greater depth. This course assumes a good background in basic probability and a strong ability to program in Java. Prior experience with linguistics or natural languages is helpful, but not required.  There will be a lot of statistics, algorithms, and coding in this class.

Readings