Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

06/22/2020
by   Stephen Roller, et al.
19

We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping holes we have not filled yet. We present a biased view, focusing on work done by our own group, while citing related work in each area. In particular, we discuss in detail the properties of continual learning, providing engaging content, and being well-behaved – and how to measure success in providing them. We end with a discussion of our experience and learnings, and our recommendations to the community.

READ FULL TEXT

page 8

page 11

research
02/22/2018

Unicorn: Continual Learning with a Universal, Off-policy Agent

Some real-world domains are best characterized as a single task, but for...
research
12/28/2017

Toward Continual Learning for Conversational Agents

While end-to-end neural conversation models have led to promising advanc...
research
11/16/2018

The Barbados 2018 List of Open Issues in Continual Learning

We want to make progress toward artificial general intelligence, namely ...
research
11/09/2019

The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents

We introduce dodecaDialogue: a set of 12 tasks that measures if a conver...
research
05/11/2021

Diplomat: A conversational agent framework for goal-oriented group discussion

Recent work in human-computer interaction has explored the use of conver...
research
08/05/2022

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

We present BlenderBot 3, a 175B parameter dialogue model capable of open...
research
08/25/2021

Can a Humorous Conversational Agent Enhance Learning Experience and Outcomes?

Previous studies have highlighted the benefits of pedagogical conversati...

Please sign up or login with your details

Forgot password? Click here to reset