Would you Like to Talk about Sports Now? Towards Contextual Topic Suggestion for Open-Domain Conversational Agents

TL;DR

This paper proposes personalized, context-aware methods for topic suggestion in open-domain conversational agents, improving relevance and engagement by combining conversation context and collaborative filtering, validated on real Alexa Prize data.

Contribution

It formalizes the Conversational Topic Suggestion problem and introduces three novel approaches, including a hybrid model, to enhance topic recommendation accuracy in open-domain dialogue systems.

Findings

CTS-Seq outperforms baseline by 23% in accuracy

Hybrid CTS-Seq-CF improves accuracy by 12% over CTS-Seq

Models show promising results on real Alexa Prize conversations

Abstract

To hold a true conversation, an intelligent agent should be able to occasionally take initiative and recommend the next natural conversation topic. This is a challenging task. A topic suggested by the agent should be relevant to the person, appropriate for the conversation context, and the agent should have something interesting to say about it. Thus, a scripted, or one-size-fits-all, popularity-based topic suggestion is doomed to fail. Instead, we explore different methods for a personalized, contextual topic suggestion for open-domain conversations. We formalize the Conversational Topic Suggestion problem (CTS) to more clearly identify the assumptions and requirements. We also explore three possible approaches to solve this problem: (1) model-based sequential topic suggestion to capture the conversation context (CTS-Seq), (2) Collaborative Filtering-based suggestion to capture previous successful conversations from similar users (CTS-CF), and (3) a hybrid approach combining both conversation context and collaborative filtering. To evaluate the effectiveness of these methods, we use real conversations collected as part of the Amazon Alexa Prize 2018 Conversational AI challenge. The results are promising: the CTS-Seq model suggests topics with 23% higher accuracy than the baseline, and incorporating collaborative filtering signals into a hybrid CTS-Seq-CF model further improves recommendation accuracy by 12%. Together, our proposed models, experiments, and analysis significantly advance the study of open-domain conversational agents, and suggest promising directions for future improvements.