Instructors:

David DeVault (Research Assistant Professor, Computer Science, devault@ict.usc.edu)
David Traum (Research Assistant Professor, Computer Science, traum@ict.usc.edu)

Location and Time:

  • Meeting time: Wednesday 3:30 - 6:20pm
  • Place: GFS 213
  • Office Hours:
    • in SAL 214 or 216 on Wednesdays 2:00-3:15, or
    • in GFS 213 after class, or
    • by appointment (at ICT in Playa Vista)

Prerequisites:

Students should have some experience with natural language processing or artificial intelligence, and should be comfortable with medium-sized programming projects. Recommended background would be at least one of the following courses: CSCI 544 (Natural Language Processing) or CSCI 561 (Foundations of Artificial Intelligence) or CSCI 562 (Empirical Methods in Natural Language Processing) or EE619 (Advanced Topics in Speech Recognition). Students who have not taken one of these courses should request permission from the instructors.

Description:

This course will introduce students to existing computational techniques and active research areas in the design of natural language dialogue systems. Natural language dialogue involves extended communication between two or more participants using a natural language such as English. Dialogue systems are designed to participate in extended natural language interactions with human users, and have been developed for a variety of interactive settings where a conversational interface offers advantages. Dialogue systems leverage a range of natural language processing and modeling techniques to help them serve as fluent and efficient conversational partners. This course will introduce students to these techniques, with topics to include spoken language understanding, modeling dialogue genres, dialogue management and representing context, dialogue response policies, natural language generation, embodied conversational agents, incremental speech processing, and dialogue system evaluation.

Dialogue systems are both an old topic in AI and Computer Science (with famous early examples such as Eliza, Lunar, and SHRDLU) and a topic of much current interest and research. Indeed, dialogue systems have recently become a commercial reality, with companies such as Nuance, Microsoft, AT&T, Google, Apple, and others providing ubiquitous speech recognition services and voice-driven information access systems. These services are increasingly accessible (on the web, mobile devices, and anywhere Internet connectivity can be established), and they provide exciting new possibilities for dialogue systems to be made available to large user populations. Throughout the course, students will acquire an appreciation for some of the capabilities and potential of these new technologies, as well as their current limitations.

Students should come away from the course with a basic understanding of dialogue system design and evaluation, and be able to:

  • implement simple dialogue systems
  • read and assess research papers in the area
  • embark on new research in the area

Course Format:

The course lecture periods will consist of approximately 1/2 lectures by the instructors, and 1/2 group discussion of research papers, mostly led by students. For all class periods, students will be responsible for sending in discussion questions on the readings, as well as participating in class discussions. Each student will have to lead the discussion of one advanced research topic, including a short review presentation on the topic. Students will also complete several small assignments, and carry out a main project on a topic agreed by the instructors.

Course Requirements:

Grading
1. reading and reviewing assigned papers10%
2. participation in class discussions 10%
3. leading one discussion topic based on assigned readings20%
4. 2-3 small assignments20%
5. main project40%

Course Materials:

Required readings: The primary readings for this course will be a set of technical papers to accompany each lecture session and student-led topic. These papers will be made available on the web or as handouts.

Optional text: Spoken Dialogue Systems, Kristiina Jokinen and Michael McTear, Synthesis Lectures on Human Language Technologies, 2009, Vol. 2, No. 1 , Pages 1-151. This text is freely available to USC students at: http://www.morganclaypool.com/doi/pdf/10.2200/S00204ED1V01Y200910HLT005