Deep Neural Network class METHOD AND APPARATUS FOR CLASSIFYING A CLASS TO WHICH A SENTENCE BELONGS BY USING DEEP NEURAL NETWORK

摘要

Provided are a method and apparatus for classifying a class to which a sentence belongs by using a deep neural network. According to an embodiment of the present disclosure, the first and second sentences are learned through the first neural network and the second neural network, respectively, and the first feature vector and the second generated as output data of the learning. Provided are a method and apparatus for acquiring a contrasting loss based on whether a feature vector is identical to a class to which a first sentence and a second sentence belong, and repeating learning to maximize the contrast loss.