Go to Main Content

Georgetown University

HELP | EXIT

Detailed Course Information

 

Fall 2020
May 22, 2022
Transparent Image
Information Select the desired Level or Schedule Type to find available classes for the course.

COSC 483 - Dialogue Systems
Nearly all of us interact with dialogue systems -- from calling up banks and hotels, to talking with intelligent assistants like Siri, Alexa, or Cortana, dialogue systems enable people to get tasks done with software agents using language. Since the interaction is bi-directional, we must consider the fundamentals of how people engage in conversation so as to manage users’ expectations and track how information is exchanged in dialogue. Dialogue systems require an array of technologies to come together for them to work well, including speech recognition, natural language understanding, dialogue management, natural language generation, and speech synthesis. This course will explore what makes dialogue systems effective in commercial and research applications (ranging from personal assistants and chatbots to embodied conversational agents and language-directed robots) and how this contrasts with everyday human-human dialogue.

This course will introduce students to the fundamentals of dialogue systems, expanding on technologies and algorithms that are used in today’s dialogue systems and chatbots. There will also be emphasis on the psycholinguistic properties of human conversation (turn-taking, grounding) so as to prepare students for designing effective, user-friendly dialogue systems. The course will also include examining datasets and dialogue annotations used to train dialogue systems with machine learning algorithms. Coursework will consist of lectures, writing and programming assignments, and student-led presentations on special topics in dialogue. A final project will give students a chance to build their own dialogue system using open source and freely available software. This course is intended for students that are already comfortable with limited amounts of programming (in Python).

3.000 Credit hours
3.000 Lecture hours

Levels: MN or MC Graduate, Undergraduate
Schedule Types: Lecture

Computer Science Department

Course Attributes:
Mean Grade is Calculated

Prerequisites:
LING 362 or LING 572 or COSC 572

Return to Previous New Search
Transparent Image
Skip to top of page
Release: 8.7.2.4