Conversational AI

Conversational AI

This project develops next-generation conversational AI models that combine cognitive intelligence with practical real-world applications. The research focuses on creating foundation models and innovative approaches that enable AI agents to understand context, reason adaptively, and engage in natural human-like dialogue across extended conversations. Key innovations include cognitive-inspired dialogue management, dynamic reasoning, multimodal understanding, and context-aware response generation that can infer implicit information and adapt communication styles. These systems are designed for seamless integration into diverse applications, from virtual assistants and educational platforms to healthcare and enterprise solutions. By bridging advanced AI research with practical implementation, the project aims to create foundational conversational AI technologies that are immediately deployable and scalable across industries, enhancing human-computer interaction through more intelligent, contextually aware, and genuinely helpful dialogue systems.RetryClaude can make mistakes. Please double-check responses.

Director

  • Jinho Choi - Associate Professor at Emory University

Publications

  1. Finding A Voice: Exploring the Potential of African American Dialect and Voice Generation for Chatbots. Finch S. E.; Paek, E. S.; and Choi, J. D. Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
  2. Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions. Finch, J. D.; Josyula, Y.; and Choi, J. D. Transactions of the Association for Computational Linguistics (TACL), 2025.
  3. Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models. S. E. Finch and Choi, J. D. Proceedings of the International Conference on Computational Linguistics (COLING), 2025.
  4. Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Tracking. Finch, J. D.; and Choi, J. D. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP): Findings, 2024.
  5. Transforming Slot Schema Induction with Generative Dialogue State Inference. Finch, J. D.; Zhao, B.; Choi, J. D. Proceedings of the Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2024.
  6. ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI. Finch, S. E. and Choi, J. D. Transactions of the Association for Computational Linguistics (TACL), 2024.