Lab for Natural Language Engineering, Assignment 1 Group 9

GRIPS link: https://elearning.uni-regensburg.de/course/view.php?id=72799

Files and Dataset

We have 3 main files in this repository:

1. gemma_annotation.csv -> the original dataset file given by the professor
2. gemma_annotation_normalized.csv -> the one we produce after processing original file in task 1
3. failed_extracts_final.csv -> the final file after querying the LLM to preprocess and testing with the API to reduce number of unknown ingredients