In the benchmarks, when we see ROUGE scores (ROUGE-1, ROUGE-2, ROUGE-L), what is the actual underlying score? Recall or Precision or F1 or some other transformation of some combination of these values?

ROUGE score - what does it refer to - Recall / Precision / F1 or something else?

Course Q&A Generative AI with Large Language Models

gent.spah January 8, 2024, 3:24pm 2

This is an article that explains each one of them and their respective formulas with regards to precision, recall and F1. To go straight to the endpoint:

Mean of the F1 scores will gives us the full ROUGE-1 score for dataset. (similar to ROUGE-2…)

Topic		Replies	Views
ROUGE-L Calculation in the lecture : "Model Evaluation" of Week-2 Generative AI with Large Language Models week-module-2	4	540	December 15, 2023
C4_W1rouge1_similarity NLP with Attention Models week-module-1	5	416	September 4, 2024
UNQ_C8 - Rouge similarity NLP with Attention Models week-module-1	2	663	May 21, 2022
Bleu and rouge scores NLP with Attention Models week-module-1	2	630	January 16, 2023
Error in video's ROUGE-1 `precision` calculation Generative AI with Large Language Models week-module-2	2	17	February 10, 2025

ROUGE score - what does it refer to - Recall / Precision / F1 or something else?

Related topics