General

• Book: https://emory.gitbook.io/conversational-ai

• GitHub:

• Time: MW 2:30PM - 3:45PM

• Location: White Hall 112

Instructors

• Associate Professor of Computer Science Office Hours → MW 4PM - 5:30PM, MSC W302F

• Research Engineer at the Emory NLP Research Lab Office Hours → TuTh 1PM - 2:30PM, MSC W302B ()

• Ph.D. student of Computer Science and Informatics Office Hours → MW 11:30AM - 1PM, MSC W302B

Grading

• 1 + 7 topical quizzes: 55%

• 3 LINC discussions: 10%

• Project proposal: 15%

Topical Quizzes

• For every topic, one quiz will be assigned to check if you keep up with the materials.

• Quizzes must be submitted individually. Discussions are allowed; however, your work must be original.

• Late submissions within a week will be accepted with a grading penalty of 15% and will not be accepted once the solutions are discussed in class.

LINC Discussions

• You will meet with students from three times:

  • 02/08 (W): evening (60 mins), 6PM, Atwood 215

  • 03/15 (W): evening (60 mins), 6PM, Atwood 215

Project Proposal

• You are expected to:

  • Group a team of 3-4 members.

  • Give a presentation to propose your idea about the final project.

Final Project

• You are expected to:

  • Give a presentation about your final project.

  • Give a demonstration of your system.

Artificial Intelligence (AI) has advanced to the point that it starts interacting with humans in natural language. This communication ability makes AI an integral part of human society as a collaborator and companion. Thus, it is essential to understand how AI can (and should) be designed to conduct meaningful conversations with humans. The main objectives of this course are:

• To discover technical approaches to dialogue systems.

• To conceive manifold use cases of dialogue systems.

• To study effective ways of Human-Computer Interaction.

• To develop a dialogue system using methods in Computational Linguistics.

• To comprehend the limitations of your dialogue system through Statistical Analysis.

Students will have individual assignments and work in groups to build end-to-end dialogue systems of their choice. Toward the end of the semester, all teams will present the dialogue systems with live demonstrations.

LINC Course

For Spring 2023, this is selected as a course. Thus, it will include collaborative work with students taking .