This course gives a graduate level overview of concepts and techniques for statistical modeling of structured data.

Much of the data we see is in an unstructured form – text, images, videos, etc. How do we efficiently learn to extract structured information from such raw data? This could involve tasks such as parsing a sentence, creating a tabulated summary of the information in a webpage, adding tags to an image, recognizing objects in images, etc. The common thread across these applications is that predicting the output requires assignments to multiple interdependent variables.

In this course, we will study topics in structured learning and prediction, with a focus on ideas that have emerged in the last couple of decades. We will look at several techniques for structured output learning and prediction using examples from natural language processing, computer vision and related areas.

See course information for details about course mechanics and policies.


Meetings & Staff

Lectures: Mon & Wed, 11:50AM – 01:10PM at WEB L103

Instructor: Vivek Srikumar

Office 3126 MEB
Email svivek at cs dot utah dot edu
Office hours Wed 2:00 PM, 3126 MEB, or by appointment

Teaching Assistant: Xingyuan Pan

Email xpan at cs dot utah dot edu
Office Hours Tue 1:30 PM – 2:30 PM (MEB 3115)

Please prefix any emails to the instructor or the TA with the course number CS 6961.

Discussion forum: We will be using Canvas. Please use the discussion forum as the preferred medium for interacting with the instructor and the teaching assistants rather than emailing directly.


Course objectives, or: What can I expect to learn?

The first third of the semester will consist of lectures. After that, lectures will be followed by student presentations in class. At the end of the course, you should be able to critically read current literature and use the ideas learned to:

  1. Define structured models for new problems,

  2. Identify or develop learning paradigms given constraints on available data and time for training, and

  3. Identify or develop inference algorithms for predicting outputs given computational constraints.