Method And System For Performing Information Extraction And Quality Control For A Knowledge Base
First Claim
1. A system for extracting information from articles and for storing the extracted information in a frame-based knowledge representation, the system comprising:
- an article selection unit, for selecting and prioritizing articles from which information will be extracted;
an information extraction unit coupled to and in communication with the article selection unit, which receives selected articles from the article selection unit and extracts information from the selected article according to pre-defined information extraction protocols;
a knowledge representation management unit, coupled to and in communication with the information extraction unit for determining if the extracted information has been both properly extracted and formatted for storage in the frame-based knowledge representation;
an information storage unit coupled to and in communication with the knowledge representation management unit for storing the information in the representation if it has been properly extracted and formatted and for responding to inquiries regarding the stored representation; and
a query management and information display unit, coupled to and in communication with the information storage unit for responding to user inquiries for information stored in the information storage unit, for retrieving information from the information storage unit in response to the queries and for displaying the retrieved information.
1 Assignment
0 Petitions
Accused Products
Abstract
The present invention relates to the field of information extraction and storage id more specifically to techniques for extracting information from a plurality of articles in a distributed manner and for storing the extracted information in an information store an embodiment of the present invention identifies a plurality of articles from which information to be extracted and a plurality of information extractors for extracting the information from e articles. A database is provided for storing information related to the plurality of articles and the plurality of information extractors. The plurality of articles are assigned to the plurality of information extractors for information extraction. Information extracted by formation extractors from the articles is stored in the information store.
-
Citations
8 Claims
-
1. A system for extracting information from articles and for storing the extracted information in a frame-based knowledge representation, the system comprising:
-
an article selection unit, for selecting and prioritizing articles from which information will be extracted; an information extraction unit coupled to and in communication with the article selection unit, which receives selected articles from the article selection unit and extracts information from the selected article according to pre-defined information extraction protocols; a knowledge representation management unit, coupled to and in communication with the information extraction unit for determining if the extracted information has been both properly extracted and formatted for storage in the frame-based knowledge representation; an information storage unit coupled to and in communication with the knowledge representation management unit for storing the information in the representation if it has been properly extracted and formatted and for responding to inquiries regarding the stored representation; and a query management and information display unit, coupled to and in communication with the information storage unit for responding to user inquiries for information stored in the information storage unit, for retrieving information from the information storage unit in response to the queries and for displaying the retrieved information. - View Dependent Claims (2, 3)
-
-
4. A method for constructing a frame-based knowledge representation, the method comprising the steps of:
-
selecting articles to serve as an information source for the knowledge representation; extracting information from the selected articles and formatting it for storage in the knowledge representation; verifying that the information extracted from the selected articles is correct and that it has been placed in the correct format; and
storing the formatted information in—
the knowledge representation. - View Dependent Claims (5, 6, 7, 8)
-
Specification