METHOD TO LEVERAGE SIMILARITY AND HIERARCHY OF DOCUMENTS IN NN TRAINING

摘要

A computer-implemented method for training a natural language-based classifier, includes obtaining a query and a first label which is a binary vector, each of a plurality of elements of the binary vector being associated with one of a plurality of instances, the first label indicating that the query is classified into a specific instance of the plurality of instances by a value set to a specific element associated with the specific instance, estimating relationships between the specific instance and instances other than the specific instance of the plurality of instances, generating a second label which is a continuous-valued vector from the first label by distributing the value set to the specific element to elements other than the specific element of the plurality of elements according to the relationships, and training the natural language-based classifier using the query and the second label.