System and method for facts extraction and domain knowledge repository creation from unstructured and semi-structured documents
AssigneeGlenbrook Networks
InventorsJulia Komissarchik, Edward Komissarchik
Life of this patent
Estimating the term…
Abstract
Provided are methods and systems that extract facts of unstructured documents and build an oracle for various domains. The present invention addresses the problem of efficient finding and extraction of facts about a particular subject domain from semi-structured and unstructured documents, makes inferences of new facts from the extracted facts and the ways of verification of the facts, thus becoming a source of knowledge about the domain to be effectively queried. The methods and systems can also extract temporal information from unstructured and semi-structured documents, and can find and extract dynamically generated documents from Deep or Dynamic Web.
Claims7
A method for reducing a number of false positives in a fact extraction process, comprising:
- utilizing a deferred decision method;
- building several levels of verification steps to eliminate incorrect candidate facts;
- applying a set of knowledge agents of different type to verify results of each other;
- utilizing N-best results to support a deferred decision method;
- and
- accommodating a detailed rerun of appropriate knowledge agents to retrieve additional parameters to resolve fact discrepancies.
A method for extraction of very important numbers and objects that are associated with from a page comprising:
- determining paragraphs and tables containing numbers;
- and extracting the numbers.
Dependencies are inferred from the claim text.