Athena 2.0: Discourse and User Modeling in Open Domain Dialogue

TL;DR

Athena 2.0 is an advanced open-domain conversational agent that employs a knowledge-grounded discourse model and user modeling to enhance coherence, personalization, and entity tracking in socialbot interactions.

Contribution

It introduces a novel discourse and user modeling framework that improves entity tracking and personalization in open-domain dialogue systems.

Findings

Enhanced entity linking accuracy

Improved user engagement through personalization

Effective handling of diverse topics

Abstract

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.