Skip to content

Latest commit

 

History

History
3 lines (2 loc) · 509 Bytes

README.md

File metadata and controls

3 lines (2 loc) · 509 Bytes

To conduct the analysis of statistical features of both the raw dataset and refined dataset, Evaluator employs a visualization approach to present the data distribution (perplexity, language, etc.) in a user-friendly manner.

Additionnally, Evaluator evaluates the texts in three manners, language identifier by fasttext, perplexity evalutor by kenlm and text scores by ChatGPT.