SUMMARIZING TEXT DOCUMENTS BY RESOLVING CO-REFERENTIALITY AMONG ACTORS OR OBJECTS AROUND WHICH A STORY UNFOLDS
Patent №
US 6,185,592
Granted
2001-02-06
Filed 1997
Owner
APPLE COMPUTER, INC.
Lab
—
AI components
3
ml · nlp · kr
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
08974079
A method and system for characterizing the content of a document is disclosed. The method and system comprise identifying a plurality of discourse referents in the document, dividing the document into topically relevant document segments, and resolving co-referentiality among the discourse referents within, and across, the document segments. The method and system also comprises calculating salience values for the discourse referents based upon the resolving step, and determining topic stamps for the document segments based upon the salience values of the associated discourse referents. Finally the method and system comprise providing summary-like abstractions, in the form of capsule overviews of each of the segments derived from its topic stamps. In so doing, a capsule overview is derived for the entire document, which will depict the core content of an average length article in a more accurate and representative manner than utilizing conventional techniques.
AI classification
Ownership
APPLE COMPUTER, INC.
assignment · 88830316
Assignors
BOGURAEV, BRANIMIR, KENNEDY, CHRISTOPHER DAVID
On an employer assignment, the assignors are typically the inventors.