CLAIHCOct 7, 2019

Gunrock: A Social Bot for Complex and Engaging Long Conversations

arXiv:1910.03042v11010 citations
Originality Incremental advance
AI Analysis

This addresses the problem of creating more natural and satisfying AI-driven conversations for general users, though it appears incremental with system design improvements.

The paper tackles the challenge of building a social bot for complex, engaging long conversations, winning the 2018 Amazon Alexa Prize by achieving higher coherence and engagement, with users producing longer sentences correlated to better ratings and more turns.

Gunrock is the winner of the 2018 Amazon Alexa Prize, as evaluated by coherence and engagement from both real users and Amazon-selected expert conversationalists. We focus on understanding complex sentences and having in-depth conversations in open domains. In this paper, we introduce some innovative system designs and related validation analysis. Overall, we found that users produce longer sentences to Gunrock, which are directly related to users' engagement (e.g., ratings, number of turns). Additionally, users' backstory queries about Gunrock are positively correlated to user satisfaction. Finally, we found dialog flows that interleave facts and personal opinions and stories lead to better user satisfaction.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes