ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
Published in EMNLP, 2023
This paper presents ConvLab-3, a dialogue system toolkit that simplifies the integration of diverse datasets and models, and facilitates the study of generalization and transfer in dialogue systems.
Recommended citation: Qi Zhu, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Shutong Feng, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gasic, and Minlie Huang. (2023). "ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format." In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 106–123, Singapore. Association for Computational Linguistics. https://aclanthology.org/2023.emnlp-demo.9