Atlassian Corporation
CONTENT DISCOVERY SYSTEMS AND METHODS

Abstract:

Described herein is a computer implemented method comprising accessing a document, generating a document vector in respect of the document, and generating a sentence vector for each sentence in the document. The method further comprises calculating a sentence similarity score for each sentence in the document which, for a given sentence, is calculated based on a similarity between the sentence vector for the given sentence and the document vector, and identifying one or more representative document sentences for inclusion in a document summary.