CS Events

Qualifying Exam

Towards a Conversation Analysis Approach for Multicommunicating in Open-Domain, Retrieval-Based Conversational Agents

 

Download as iCal file

Monday, May 18, 2020, 10:00am - 12:00pm

 

Speaker: Carlos M. Muniz

Location : Remote via Webex

Committee

Dr. Mubbasir Kapadia, Dr. Gerard de Melo, Dr. Karl Stratos, and Dr. Sepehr Assadi (External Member)

Event Type: Qualifying Exam

Abstract: Multicommunication is a prevalent behavior found in online human conversation, and yet most human-to-chatbot approaches do not address it. Intrinsic parts of human-to-human conversations like the flexibility of communication tempo, the compartmentalization of conversation, and the topics and intensity of interactions are elevated in multicommunicative human-to-chatbot conversations. Previous Deep Learning approaches may overlook these intrinsic characteristics due to them focusing on the evaluation of human-likeness through sensible and specific responses [Google’s Meena] or on-topic responses [Amazon’s Alexa Prize Challenge]. In order to both capture the human-likeness of sensible, specific, and on-topic responses, we use the fundamental unit of conversation as defined by Conversational Analysis: the adjacency pair; and expand it into an Adjacency Relation to describe a succession of adjacency pairs. To illustrate this Conversational Analysis and Multicommunication Theory, we are developing an Interactive Behavior Tree Conversation Management Framework for Multicommunicating in an Open-Domain, Retrieval-Based Chatbot. We will describe a preliminary deployment of this framework and highlight its advantages (and limitations). We show that this framework provides additional human-likeness not provided by other response retrieval techniques and show this using our own Multi-Engagement Metric. Furthermore, we describe a real problem where a solution of this type will be applied and studied.

 

Meeting number: 794 381 085
Password: Uk7SNKYPU63

https://rutgers.webex.com/rutgers/j.php?MTID=me453647c2316defebcdcc5285405938f

Join by video system
Dial This email address is being protected from spambots. You need JavaScript enabled to view it.
You can also dial 173.243.2.68 and enter your meeting number.

Join by phone
+1-650-429-3300 USA Toll
Access code: 794 381 085