[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[[["\u003cp\u003eThe \u003ccode\u003eRougeSpec\u003c/code\u003e class in the Vertex AI v1beta1 API calculates the recall of n-grams in predictions compared to a reference, providing a score between 0 and 1.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eRougeSpec\u003c/code\u003e is a sealed class that implements multiple interfaces, including \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, and inherits members from the \u003ccode\u003eobject\u003c/code\u003e class.\u003c/p\u003e\n"],["\u003cp\u003eThe class supports specifying different Rouge types (e.g., rougen[1-9], rougeL, rougeLsum) through its \u003ccode\u003eRougeType\u003c/code\u003e property.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eSplitSummaries\u003c/code\u003e and \u003ccode\u003eUseStemmer\u003c/code\u003e are optional boolean properties that control splitting of summaries when using rougeLsum and applying stemming respectively.\u003c/p\u003e\n"],["\u003cp\u003eThere are 2 constructors for this class, one default and one that takes in another \u003ccode\u003eRougeSpec\u003c/code\u003e object.\u003c/p\u003e\n"]]],[],null,[]]
