Major point extraction device, major point extraction method, and non-transitory computer readable recording medium

Abstract

The present invention allows appropriate acquisition of focus points in a dialogue. The focus point extraction devicecomprises: a dialogue scene predict unit () for predicting the dialogue scene of an utterance included in dialogue; an utterance type prediction sort unit () for predicting whether utterances are to be subjected to utterance type prediction; an utterance type predict unit () for predicting the utterance type of the utterance having been predicted as one to be subjected to the utterance type prediction; an utterance content extraction necessity predict unit () for predicting, in a case in which it has been predicted that the utterance belongs to any utterance type, whether a portion of the utterance is to be subjected, as utterance focus point information, to extraction or classification; and an utterance content extract unit () for: extracting or classifying the portion of the utterance from the utterance as the utterance focus point information, in a case in which it is predicted that a portion of the utterance is to be subjected to extraction or classification; and extracting or classifying the entirety of the utterance as the utterance focus point information, in a case in which it is predicted that a portion of the utterance is not to be subjected to extraction or classification.