Scribd
Upload
155 views9 pages

Evaluation Metrics Formulas

The document outlines key evaluation metrics for text summarization, including ROUGE, BLEU, Precision, Recall, and F1 Score, along with their respective formulas. Each metric serves a specific purpose, such as measuring similarity, relevance, and overall performance of AI models. The conclusion emphasizes the importance of using a combination of these metrics for reliable evaluation.

Uploaded by

veldutinagasai97
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
155 views9 pages

Evaluation Metrics Formulas

The document outlines key evaluation metrics for text summarization, including ROUGE, BLEU, Precision, Recall, and F1 Score, along with their respective formulas. Each metric serves a specific purpose, such as measuring similarity, relevance, and overall performance of AI models. The conclusion emphasizes the importance of using a combination of these metrics for reliable evaluation.

Uploaded by

veldutinagasai97
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Evaluation Metrics: Formulas

• Understanding key evaluation metrics:


ROUGE, BLEU, F1 Score, Precision, and Recall.
ROUGE (Recall-Oriented Understudy for
Gisting Evaluation)
• Formula: ROUGE-N = (∑ Overlapping n-
grams) / (∑ Reference n-grams)

• Measures recall-based similarity for text


summarization.
BLEU (Bilingual Evaluation Understudy)
• Formula: BLEU = BP * exp(∑ log(Pn) / N)

• Where BP is Brevity Penalty, and Pn is n-gram


precision.

• Measures n-gram overlap between generated


and reference text.
Precision
• Formula: Precision = TP / (TP + FP)

• Where TP = True Positives, FP = False Positives.

• Measures how many retrieved results are


relevant.
Precision
• Formula: Precision = TP / (TP + FP)

• Where TP = True Positives, FP = False Positives.

• Measures how many retrieved results are


relevant.
Recall
• Formula: Recall = TP / (TP + FN)

• Where TP = True Positives, FN = False


Negatives.

• Measures how many relevant results were


retrieved.
F1 Score
• Formula: F1 = 2 * (Precision * Recall) /
(Precision + Recall)

• Balances precision and recall for overall


performance evaluation.
Conclusion
• Using a combination of these metrics ensures
reliable AI model evaluation.
Q&A
• Open floor for discussion and questions.

You might also like