Chujie Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chujie Zheng has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Minlie Huang
The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China
3 shared publications - Bo Wang
Department of Computer Science, University of Toronto, Toronto, Canada
1 shared publication - Hao Zhou
Shanghai Jiao Tong University
1 shared publication Jiaxin Wen
DCST Institute for Artificial Intelligence Beijing National Research Center for Information Science and Technology The CoAI group State Key Lab of Intelligent Technology and Systems Tsinghua University 100084 Beijing China
1 shared publication- Jinfeng Zhou
China Biodiversity Conservation and Green Development Foundation, Beijing, China
1 shared publication Kaili Huang
Conversational AI Group, AI Lab., Dept. of Computer Science, Tsinghua University Beijing National Research Center for Information Science and Technology, China
1 shared publication
Latest Publications
- Open Access
AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation
Crowdsourced dialogue corpora are usually limited in scale and topic coverage due to the expensive cost of data curation. This would hinder the generalization of downstream dialogue models to open-domain topics. In this work, we leverage large language models for dialogue augmentation in the task of emotional support conversation (ESC). By treating dialogue augmentation as a dialogue completion task, we prompt a fine-tuned language model to complete full dialogues from available dialogue posts of various topics, which are then postprocessed based on heuristics. Applying this approach, we construct AugESC, an augmented dataset for the ESC task, which largely extends the scale and topic coverage of the crowdsourced ESConv corpus. Through comprehensive human evaluation, we demonstrate that our approach is superior to strong baselines of dialogue augmentation and that AugESC has comparable dialogue quality to the crowdsourced corpus. We also conduct human interactive evaluation and prove that post-training on AugESC improves downstream dialogue models' generalization ability to open-domain topics. These results suggest the utility of AugESC and highlight the potential of large language models in improving data-scarce dialogue generation tasks.
Open AccessAugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation
Crowdsourced dialogue corpora are usually limited in scale and topic coverage due to the expensive cost of data curation. This would hinder the generalization of downstream dialogue models to open-domain topics. In this work, we leverage large language models for dialogue augmentation in the task of emotional support conversation (ESC). By treating dialogue augmentation as a dialogue completion task, we prompt a fine-tuned language model to complete full dialogues from available dialogue posts of various topics, which are then postprocessed based on heuristics. Applying this approach, we construct AugESC, an augmented dataset for the ESC task, which largely extends the scale and topic coverage of the crowdsourced ESConv corpus. Through comprehensive human evaluation, we demonstrate that our approach is superior to strong baselines of dialogue augmentation and that AugESC has comparable dialogue quality to the crowdsourced corpus. We also conduct human interactive evaluation and prove that post-training on AugESC improves downstream dialogue models' generalization ability to open-domain topics. These results suggest the utility of AugESC and highlight the potential of large language models in improving data-scarce dialogue generation tasks.
- Top Cited PapersOpen Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 8223-8237
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
Jinfeng Zhou, Chujie Zheng, Bo Wang, Zheng Zhang, Minlie Huang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 8223-8237
Top Cited PapersOpen AccessCASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
Jinfeng Zhou, Chujie Zheng, Bo Wang, Zheng Zhang, Minlie Huang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- Open Access
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 7098-7108
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
Hao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang, Xiaoyan Zhu. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 7098-7108
Open AccessKdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
Hao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang, Xiaoyan Zhu. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.