UNSUPERVISED TEXT SUMMARIZATION METHOD BASED ON SENTENCE EMBEDDING AND UNSUPERVISED TEXT SUMMARIZATION DEVICE USING THE SAME

摘要

The present invention provides a document summarization method implemented by a processor, comprising: receiving a document including a plurality of sentences, clustering a plurality of sentences in a document using a pre-learned language model configured to cluster sentences, Using a summary model configured to generate a summary statement in an unsupervised learning method based on the sentence cluster, generating a summary statement for each of the plurality of clustered sentences, and obtaining a final summary statement for the document, in each of the plurality of sentences. It provides a document summarization method and an apparatus using the same, including the step of reconfiguring the summary of the text.