There is a newer version of the record available.

Published March 29, 2023 | Version 1.0

GPT Capabilites for Extracting Tasks From Textual Process Descriptions

  • 1. Technical University of Munich
  • 2. Austrian Center for Digital Production

Description

This dataset provides three tables which evaluate the capabilities of GPT 1, GPT 2, GPT 3, and GPT 4 regarding the extraction of tasks from https://doi.org/10.5281/zenodo.7783492 dataset.

The performance of the LLMs is measured by calculating a range of similarity metrics:

  • Extracted number of tasks from text vs. extracted number of tasks from Model
  • Semantic Text Similarity: Contextual and Non-Contextual between extracted sets of tasks
  • Semantic Text Similarity: Contextual and Non-Contextual between extracted individual tasks
  • Similarities and Prevalence for length restricted extracted labels
  • Similarities and Prevalence for augmented texts (each text has been paraphrased by 9 different paraphrasing methods)

Files

Files (412.1 kB)

Name Size Download all
md5:f12a529b368b36395cc7af4b16268852
99.7 kB Download
md5:cd1033373d40ec41c015d3cbf4dea033
208.2 kB Download
md5:8c3b3a5b4d1583cd6a196940a713f945
104.2 kB Download