AUTHORING SYSTEM FOR BAYESIAN NETWORKS AUTOMATICALLY EXTRACTED FROM TEXT

摘要

A system and computer program product that facilitates authoring of a Bayesian Belief Networks by: accessing text content stored in a content storage device; identifying statements within said accessed text content indicating a dependence relation; extracting said statements indicating said dependence relation from said text content; and aggregating said extracted statements into a form suitable for representation as a BBN network structure. To identify statements indicating a dependence relation, the system identifies one or more lexical and semantic attributes of variables within a text unit indicating a conditional dependence relation between two or more variables. The system further processes the text content to extract probabilistic information and probability statements and aggregate the probability statements into a quantitative layer of the BBN structure.

主权项

1. A Bayesian Belief Network (BBN) authoring system comprising:
one or more content sources providing content; a programmed processing unit for communicating with said content sources and configured to: access text content stored in a content storage device; identify statements within said accessed text content indicating a probabilistic dependence relation; extract said statements indicating said probabilistic dependence relation from said text content; and aggregate said extracted statements to form a BBN network structure.