Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations
Preprint
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.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- ChatGPT outperforms crowd workers for text-annotation tasksProceedings of the National Academy of Sciences, 2023
- A Holistic Approach to Undesired Content Detection in the Real WorldProceedings of the AAAI Conference on Artificial Intelligence, 2023
- Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data2023
- Beyond Goldfish Memory: Long-Term Open-Domain Conversation2022
- Long Time No See! Open-Domain Conversation with Long-Term Persona Memory2022
- Recipes for Building an Open-Domain Chatbot2021
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills2020
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation2016
- A large annotated corpus for learning natural language inference2015