Xiaoyao Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xiaoyao Feng has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Hanbing Liu
Renmin University of China, Beijing, China
1 shared publication - Ju Fan
Renmin University of China
1 shared publication - Nan Tang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
1 shared publication - Sibei Chen
Renmin University of China, Beijing, China
1 shared publication - Waiting Jin
Renmin University of China, Beijing, China
1 shared publication - Xiangyu Sun
Renmin University of China, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 9 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 484-487
ChatPipe: Orchestrating Data Preparation Pipelines by Optimizing Human-ChatGPT Interactions
Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming. Despite the impressive capabilities of large language models like ChatGPT in generating programs by inter- acting with users through natural language prompts, there are still limitations. Specifically, a user must provide specific prompts to iteratively guide ChatGPT in improving data preparation programs, which requires a certain level of expertise in programming, the dataset used and the ML task. Moreover, once a program has been generated, it is non-trivial to revisit a previous version or make changes to the program without starting the process over again. In this paper, we present ChatPipe, a novel system designed to facilitate seamless interaction between users and ChatGPT. Chat- Pipe provides users with effective recommendation on next data preparation operations, and guides ChatGPT to generate program for the operations. Also, ChatPipe enables users to easily roll back to previous versions of the program, which facilitates more efficient experimentation and testing. We have developed a web application for ChatPipe and prepared several real-world ML tasks from Kaggle, which can demonstrate the capabilities of ChatPipe.
- 9 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 484-487
Open AccessChatPipe: Orchestrating Data Preparation Pipelines by Optimizing Human-ChatGPT Interactions
Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming. Despite the impressive capabilities of large language models like ChatGPT in generating programs by inter- acting with users through natural language prompts, there are still limitations. Specifically, a user must provide specific prompts to iteratively guide ChatGPT in improving data preparation programs, which requires a certain level of expertise in programming, the dataset used and the ML task. Moreover, once a program has been generated, it is non-trivial to revisit a previous version or make changes to the program without starting the process over again. In this paper, we present ChatPipe, a novel system designed to facilitate seamless interaction between users and ChatGPT. Chat- Pipe provides users with effective recommendation on next data preparation operations, and guides ChatGPT to generate program for the operations. Also, ChatPipe enables users to easily roll back to previous versions of the program, which facilitates more efficient experimentation and testing. We have developed a web application for ChatPipe and prepared several real-world ML tasks from Kaggle, which can demonstrate the capabilities of ChatPipe.