Athena 2.0: Discourse and User Modeling in Open Domain Dialogue
This work addresses the challenge of building conversational agents that can maintain coherent and personalized interactions for users in social settings, representing an incremental advancement in dialogue systems.
The paper tackles the problem of creating a socialbot for open-domain dialogue by developing Athena 2.0, which uses a knowledge-grounded discourse model to track entity links and a user model for personalization, resulting in improved coherence and engagement in conversations.
Conversational agents are consistently growing in popularity and many people interact with them every day. While many conversational agents act as personal assistants, they can have many different goals. Some are task-oriented, such as providing customer support for a bank or making a reservation. Others are designed to be empathetic and to form emotional connections with the user. The Alexa Prize Challenge aims to create a socialbot, which allows the user to engage in coherent conversations, on a range of popular topics that will interest the user. Here we describe Athena 2.0, UCSC's conversational agent for Amazon's Socialbot Grand Challenge 4. Athena 2.0 utilizes a novel knowledge-grounded discourse model that tracks the entity links that Athena introduces into the dialogue, and uses them to constrain named-entity recognition and linking, and coreference resolution. Athena 2.0 also relies on a user model to personalize topic selection and other aspects of the conversation to individual users.