2023

ChatPipe: Orchestrating Data Preparation Program by Optimizing Human-ChatGPT Interactions

Chen, Sibei, Liu, Hanbing, Jin, Weiting et al.

Understand

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 interacting 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.

Built on

  • Optimizing machine learning workloads in collaborative environments. In SIGMOD . 1701–1716

    Behrouz Derakhshan, Alireza Rezaei Mahdiraji, Ziawasch Abedjan, Tilmann Rabl, and Volker Markl. 2020 · 2020

    Earlier work this paper cites.

Similar

Then

  • HybridPipe: Combining Human-generated and Machine-generated Pipelines for Data Preparation. In SIGMOD

    Sibei Chen, Nan Tang, Ju Fan, Xuemi Yan, Chengliang Chai, Guoliang Li, and Xiaoyong Du. 2023 (to appear) · 2023

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…