Share Email Print

Proceedings Paper

Considering context: reliable entity networks through contextual relationship extraction
Author(s): Peter David; Timothy Hawes; Nichole Hansen; James J. Nolan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Existing information extraction techniques can only partially address the problem of exploiting unreadable-large amounts text. When discussion of events and relationships is limited to simple, past-tense, factual descriptions of events, current NLP-based systems can identify events and relationships and extract a limited amount of additional information. But the simple subset of available information that existing tools can extract from text is only useful to a small set of users and problems. Automated systems need to find and separate information based on what is threatened or planned to occur, has occurred in the past, or could potentially occur. We address the problem of advanced event and relationship extraction with our event and relationship attribute recognition system, which labels generic, planned, recurring, and potential events. The approach is based on a combination of new machine learning methods, novel linguistic features, and crowd-sourced labeling. The attribute labeler closes the gap between structured event and relationship models and the complicated and nuanced language that people use to describe them. Our operational-quality event and relationship attribute labeler enables Warfighters and analysts to more thoroughly exploit information in unstructured text. This is made possible through 1) More precise event and relationship interpretation, 2) More detailed information about extracted events and relationships, and 3) More reliable and informative entity networks that acknowledge the different attributes of entity-entity relationships.

Paper Details

Date Published: 12 May 2016
PDF: 7 pages
Proc. SPIE 9851, Next-Generation Analyst IV, 985107 (12 May 2016); doi: 10.1117/12.2230923
Show Author Affiliations
Peter David, Decisive Analytics Corp. (United States)
Timothy Hawes, Decisive Analytics Corp. (United States)
Nichole Hansen, Decisive Analytics Corp. (United States)
James J. Nolan, Decisive Analytics Corp. (United States)

Published in SPIE Proceedings Vol. 9851:
Next-Generation Analyst IV
Barbara D. Broome; Timothy P. Hanratty; David L. Hall; James Llinas, Editor(s)

© SPIE. Terms of Use
Back to Top