System and method for facts extraction and domain knowledge repository creation from unstructured and semi-structured documents

• US 8,244,661 B1
• Filed: 07/09/2010
• Issued: 08/14/2012
• Est. Priority Date: 06/18/2004
• Status: Active Grant

• Current Assignee: Glenbrook Networks
• Original Assignee: Glenbrook Networks
• Inventors: Komissarchik, Julia, Komissarchik, Edward
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US12/833,910
• Time in Patent Office: 767 Days
• Field of Search: 706/46
• US Class Current: 706/46
• CPC Class Codes: G06F 16/345 Summarisation for human users

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.

Claims

1. A method of time stamp extraction and verification, comprising:

parsing a page and representing it as a sequence of paragraphs; and

building list of candidates for time stamp for each paragraph by extraction of valid triads representing year, month and day.

2. The method of claim 1, wherein time stamp candidates in a paragraph that are equal to the current day or day before are eliminated.

3. The method of claim 1, wherein the triads with inconsistent separators between year, month and day are eliminated.

4. The method of claim 1, wherein an oracle is applied to determine if a page contains more than one document.

5. The method of claim 1, wherein time stamp extraction is applied to a single document page.

6. The method of claim 5, wherein if a paragraph is of more than a predefined length and no time stamp candidates were extracted in paragraphs above it, declares that the page does not have time stamp.

7. The method of claim 5, wherein if a paragraph contains one time stamp candidate, declares the candidate as page document time stamp and finishes time stamp extraction.

8. The method of claim 5, wherein if there are several time stamps in a paragraph, declares that the page document does not have a time stamp.

9. The method of claim 1, wherein time stamp extraction is applied to multi-document page.

10. The method of claim 9, wherein if a paragraph does not contain a time stamp, the time stamp attribution of the previous paragraph becomes its own time stamp attribution.