(12) United States Patent ao) Patent No.: us 6,189,002 Bi
Roitblat (45) Date of Patent: Feb. 13,2001
(54) PROCESS AND SYSTEM FOR RETRIEVAL OF DOCUMENTS USING CONTEXT-RELEVANT SEMANTIC PROFILES
(75) Inventor: Herbert L. Roitblat, Honolulu, HI (US)
(73) Assignee: Dolphin Search, Honolulu, HI (US)
( * ) Notice: Under 35 U.S.C. 154(b), the term of this patent shall be extended for 0 days.
Scheler, "Extracting semantic features from unrestricted text", WCNN96, p. 499, Sep. 1996.*
* cited by examiner
Primary Examiner—Hosain T. Alam
Assistant Examiner—Sanjiv Shah
(74) Attorney, Agent, or Firm—Lieberman & Nowak, LLP
(21) Appl. No.: 09/457,190
(22) Filed: Dec. 8, 1999
Related U.S. Application Data
(60) Provisional application No. 60/112,036, filed on Dec. 14, 1998.
(51) Int. CI.7 G06F 17/30
(52) U.S. CI 707/1; 707/5; 706/15
(58) Field of Search 707/1, 3, 5, 532,
707/4, 6, 202, 531; 706/15, 16, 25; 704/9,
231
(56) References Cited
U.S. PATENT DOCUMENTS
5,325,298 * 6/1994 Gallant 704/9
5,619,709 * 4/1997 Caid et al 707/532
5,774,845 * 6/1998 Ando et al 704/231
6,006,221 * 6/2000 Liddy et al 707/5
6,076,088 * 6/2000 Paik et al 707/5
OTHER PUBLICATIONS
Carlson et al., "A cognitively-based neural network for determining paragraph coherence", IJCNN91, pp. 1303-1308, Nov. 1991.*
A process and system for database storage and retrieval are described along with methods for obtaining semantic profiles from a training text corpus, i.e., text of known relevance, a method for using the training to guide contextrelevant document retrieval, and a method for limiting the range of documents that need to be searched after a query. A neural network is used to extract semantic profiles from text corpus. A new set of documents, such as world wide web pages obtained from the Internet, is then submitted for processing to the same neural network, which computes a semantic profile representation for these pages using the semantic relations learned from profiling the training documents. These semantic profiles are then organized into clusters in order to minimize the time required to answer a query. When a user queries the database, i.e., the set of documents, his or her query is similarly transformed into a semantic profile and compared with the semantic profiles of each cluster of documents. The query profile is then compared with each of the documents in that cluster. Documents with the closest weighted match to the query are returned as search results.
18 Claims, 6 Drawing Sheets
