On April 30^th, 2021 at 10:00 am, Sara Bouguelia, PhD Student from UCBL1 LIRIS Laboratory (Lyon, France) will hold an online seminar titled "State Machine based Human-Bot Conversation and dialog patterns". Her research topic focuses on dialog management in conversational cognitive service.

Task-oriented conversational bots (or simply chatbots) are in very high demand these days. They employ third-party APIs to serve end-users via natural language interactions. Chatbots are famed for their easy-to-use interface and gentle learning curve (it only requires one of humans’ most innate ability, the use of natural language). Studies on human conversation patterns show, however, that day-to-day dialogues are complex and of multi-turn and multi-intent nature, which pushes the need for chatbots that are more resilient and flexible to this style of conversations.

During this talk, we will present the proposed State Machine based human-bot conversation model to represent and reason about dialog patterns during a human-bot interaction. We will also present to you three types of reusable patterns for recognizing compositional conversational flows. These patterns endow bot platforms with reusable functionality to recognize compositional conversational flows, that would otherwise have to be implemented by bot developers.

The event will be broadcasted through this link

      Meeting number: 121 898 1177
      Password: 9MMvTrEsk53

Join by video system:

      Dial 1218981177@politecnicomilano.webex.com
      You can also dial 62.109.219.4 and enter your meeting number.

Join by phone:

      +44-20-7660-8149 United Kingdom Toll
      Access code: 121 898 1177