Learning and Reusing Dialog for Repeated Interactions with a Situated Social Agent


James Kennedy (Disney Research Pittsburgh)
Iolanda Leite (Disney Research Pittsburgh, KTH Royal Institute of Technology)
André Pereira (Disney Research Pittsburgh)
Ming Sun (Disney Research Pittsburgh)
Boyang Albert Li (Disney Research Pittsburgh)
Rishub Jain (Disney Research Pittsburgh, Carnegie Mellon University)
Ricson Cheng (Disney Research Pittsburgh, Carnegie Mellon University)
Eli Pincus (Disney Research Pittsburgh, USC Institute for Creative Technologies)
Liz Carter (Disney Research Pittsburgh)
Jill F. Lehman (Disney Research Pittsburgh)

International Conference on Intelligent Virtual Agents (IVA) 2017

August 27, 2017

Content authoring for conversations is a limiting factor in creating verbal interactions with intelligent virtual agents. Building on techniques utilizing semi-situated learning in an incremental crowd-working pipeline, this paper introduces an embodied agent that self-authors its own dialog for social chat. In particular, the autonomous use of crowd- workers is supplemented with a generalization method that borrows and assesses the validity of dialog across conversational states. We argue that the approach offers a community-focused tailoring of dialog responses that is not available in approaches that rely solely on statistical methods across big data. We demonstrate the advantages that this can bring to interactions through data collected from 486 conversations between a situated social agent and 22 users during a 3 week long evaluation period.

Download File "Learning and Reusing Dialog for Repeated Interactions with a Situated Social Agent-Paper"
[pdf, 891.61 KB]

Copyright Notice

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.