The process that an AI model performs the assignment (such as named entity recognition or text classification) without given answers, and gets the result out of it.


The process of the AI model is trained using given data sets to achieve better inference results.


Comparing the inference result of an AI model with the correct answers, to measure the performance of the model. The result is shown using four different indicators, Precision, Recall, Accuracy, and F1 Score.

Ground Truth

A reference point against which model predictions can be compared or assessed. It refers to the correct and verified labels or outcomes that a model aims to predict


Precision is the ratio of correctly predicted positive observations of the total predicted positive observations. Precision = True Positive / (True Positive + False Positive).


Recall is the ratio of correctly predicted positive observations to all correct predictions. Recall = TP/(TP+FN)


Accuracy is a ratio of correctly predicted observation of the total observations. Accuracy = TP+TN/TP+FP+FN+TN

F1 (F1 Score)

F1 Score is the weighted average of Precision and Recall. Therefore, this score takes both false positives and false negatives into account. F1 Score = 2*(Recall * Precision) / (Recall + Precision)

Last updated