Computational Linguistics Courses

Note: Some of these courses (including Corpus Development, Knowledge Engineering for Deep Processing, Discourse Understanding/Management, and Computer Speech Processing) will be offered on a yearly basis. Others may be offered only occasionally, and the offerings may change according to faculty and student interest.

Corpus Development, Management, and Use (3 credits)
Techniques for and issues relating to the development of corpora (sampling, representativeness, genres) and treebanks, preparing generic corpora for particular uses (e.g., text normalization), corpus search methodology, and relevant statistical methods for generalizing results from corpora. Term projects will provide hands-on experience with dealing with very large corpora.

Knowledge Engineering for Deep Processing (3 credits)
Techniques and theoretical issues relating to the development of knowledge engineering resources required for deep processing (symbolic or hybrid), focusing on grammar engineering and semantic representations.

Discourse Understanding/Management (3 credits)
Techniques and algorithms for handling issues of understanding and turn-taking which arise in the development of human-computer dialogue systems, including: pronoun resolution, text coherence, implicature/inference, dialogue management, text planning, interface design (e.g., dialogue systems).

Computer Speech Processing (EE 516) (4 credits)
Introduction to automatic speech processing. Overview of human speech production and perception. Fundamental theory in speech coding, synthesis and reproduction, as well as system design methodologies. Advanced topics include speaker and language identification and adaptation.

Language in Visual Modality (3 credits)
Applications of vision technology for handling linguistic information represented visually, including problems of OCR, handwriting recognition, signed language representation/recognition.

Courses in other departments may also count toward the degree (list of pre-approved courses TBA).

Other Electives

Students who need to complete either the CS (CS 373) or statistics (STAT 391) requirement may do so with one of the three computational linguistics electives. Students who already have a background in statistics equivalent to STAT 391 may opt to use one of their electives to take an advanced statistics course.

Data Structures and Algorithms (CSE 373) (3 credits)
Data types, abstract data types, and data structures. Efficiency of algorithms. Sequential and linked implementation of lists. Binary tree representations and traversals. Searching: dictionaries, priority queues, hashing. Directed graphs, depth-first algorithms. Garbage collection. Dynamic storage allocation. Internal and external sorting.

Probability and Statistics for Computer Science (STAT 391) (4 credits)
Concepts of probability and statistics. Conditional probability, independence, random variables, distribution functions. Descriptive statistics, transformations, sampling errors, confidence intervals, least squares and maximum likelihood. Exploratory data analysis and interactive computing.

Introduction to Statistical Learning
The course covers classification and estimation of vector observations, including both parametric and nonparametric approaches. Topics include classification with likelihood functions and general discriminant functions, density estimation, supervised and unsupervised learning, feature reduction, model selection and performance estimation. The course will have one midterm and a final project involving classification of data delivered early in the term. The lectures are mostly in the first half of the course to facilitate project work.

View list of required courses.