Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations

TL;DR

This paper introduces Conversation Chronicles, a large multi-session dialogue dataset emphasizing temporal and relational dynamics, and proposes ReBot, a model capable of understanding long-term context for more coherent multi-session conversations.

Contribution

It provides a new dataset capturing multi-session dynamics and a lightweight model that effectively leverages this data for long-term contextual understanding.

Findings

ReBot achieves high human engagement scores.

Conversation Chronicles reflects realistic multi-session dialogue properties.

ReBot maintains coherence across multiple sessions.

Abstract

In the field of natural language processing, open-domain chatbots have emerged as an important research topic. However, a major limitation of existing open-domain chatbot research is its singular focus on short single-session dialogue, neglecting the potential need for understanding contextual information in multiple consecutive sessions that precede an ongoing dialogue. Among the elements that compose the context in multi-session conversation settings, the time intervals between sessions and the relationships between speakers would be particularly important. Despite their importance, current research efforts have not sufficiently addressed these dialogical components. In this paper, we introduce a new 1M multi-session dialogue dataset, called Conversation Chronicles, for implementing a long-term conversation setup in which time intervals and fine-grained speaker relationships are incorporated. Following recent works, we exploit a large language model to produce the data. The extensive human evaluation shows that dialogue episodes in Conversation Chronicles reflect those properties while maintaining coherent and consistent interactions across all the sessions. We also propose a dialogue model, called ReBot, which consists of chronological summarization and dialogue generation modules using only around 630M parameters. When trained on Conversation Chronicles, ReBot demonstrates long-term context understanding with a high human engagement score.