ROUGE-L

A member of the ROUGE family focused on the length of the longest common subsequence in the reference text and generated text. The following formulas calculate recall and precision for ROUGE-L:

You can then use F1 to roll up ROUGE-L recall and ROUGE-L precision into a single metric:

Consider the following reference text and generated text. Text | --- | I want to understand a wide variety of things. | I want to learn plenty of things. | Therefore: - The longest common subsequence is 5 (I want to of things) - The number of words in the reference text is 9. - The number of words in the generated text is 7. Consequently:

--- ROUGE-L ignores any newlines in the reference text and generated text, so the longest common subsequence could cross multiple sentences. When the reference text and generated text involve multiple sentences, a variation of ROUGE-L called ROUGE-Lsum is generally a better metric. ROUGE-Lsum determines the longest common subsequence for each sentence in a passage and then calculates the mean of those longest common subsequences.

Consider the following reference text and generated text. Text | --- | The surface of Mars is dry. Nearly all the water is deep underground. | Mars has a dry surface. However, the vast majority of water is underground. | Therefore: