chiayewken / Span-ASTE

Code Implementation of "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

evaluation and predict test

arroyoaaa opened this issue · comments

Excuse me, how to you calculate the precision, recall and FScore?您好,请问您是用什么方法(公式)计算精确率、召回率和F1值?
And what do the last two numbers mean in predict test of each sample?(as shown below)以及在每个样本的预测结果中的最后两个数字代表什么意思呢?

捕获

Hi, the two numbers are raw scores and softmax scores: #14 (comment)

Regarding the precision/recall/f1, we use micro f1 as shown here:

def score(self, path_pred: str, path_gold: str) -> dict: