Gunrock 2.0: A User Adaptive Social Conversational System

TL;DR

Gunrock 2.0 is an adaptive social conversational system that integrates neural understanding modules and hierarchical dialog management to personalize interactions based on user profiles, improving user engagement.

Contribution

It introduces a user-adaptive dialog management framework combining neural modules and hierarchical control, enhancing personalization and ease of module design.

Findings

Achieved an average rating of 3.73 in user evaluations.

Effectively adapts topic selection based on user profiles.

Integrates multiple neural NLU modules for improved understanding.

Abstract

Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptation. Gunrock 2.0 combines various neural natural language understanding modules, including named entity detection, linking, and dialog act prediction, to improve user understanding. Its dialog management is a hierarchical model that handles various topics, such as movies, music, and sports. The system-level dialog manager can handle question detection, acknowledgment, error handling, and additional functions, making downstream modules much easier to design and implement. The dialog manager also adapts its topic selection to accommodate different users' profile information, such as inferred gender and personality. The generation model is a mix of templates and neural generation models. Gunrock 2.0 is able to achieve an average rating of 3.73 at its latest build from May 29th to June 4th.