Search system and method for retrieving relevant documents from a text data base collection comprised of patents, medical and legal documents, journals, news stories and the like. Each small piece of text within the documents such as a sentence, phrase and semantic unit in the data base is treated as a document. Natural language queries are used to search for relevant documents from the data base. A first search query creates a selected group of documents. Each word in both the search query and in the documents are given weighted values. Combining the weighted values creates similarity values for each document which are then ranked according to their relevant importance to the search query. A user reading and passing through this ranked list checks off which documents are relevant or not. Then the system automatically causes the original search query to be updated into a second search query which can include the same words, less words or different words than the first search query. Words in the second search query can have the same or different weights compared to the first search query. The system automatically searches the text data base and creates a second group of documents, which as a minimum does not include at least one of the documents found in the first group. The second group can also be comprised of additional documents not found in the first group. The ranking of documents in the second group is different than the first ranking such that the more relevant documents are found closer to the top of the list.
This is a Divisional of application Ser. No. 08/350,334 filed Dec. 6, 1994 which issued as U.S. Pat. No. 5,642,502 on Jun. 24, 1997.
This invention relates to natural language data processing, and in particular to a method and system for the retrieval of natural language data. This invention is related to U.S. patent application Ser. No. 08/148,688 filed on Nov. 5, 1993, now U.S. Pat. No. 5,576,954, which is incorporated by reference. This invention was developed with grant funding provided in part by NASA KSC Cooperative Agreement NCC 10-003 Project 2, for use with: (1) NASA Kennedy Space Center Public Affairs; (2) NASA KSC Smart O & M Manuals on Compact Disk Project; and (3) NASA KSC Materials Science Laboratory.
A method for processing a search query uses the results of a search performed on a high quality, controlled database to assess the relevance of documents retrieved from a search of an uncontrolled public database having documents of highly variable quality. The method includes the steps of parsing the search query and then searching the authoritative database to generate authoritative database results. The search query is also used to search the public database, thereby generating public database results. The quality or relevance of the public database results are then quantified on the basis of the authoritative database results, thereby generating a quality index. The results from both the authoritative and the public databases are then ranked on the basis of this quality index.
An information retrieval system processes user input queries, and identifies query feedback, including ranking the query feedback, to facilitate the user in re-formatting a new query. A knowledge base, which comprises a plurality of nodes depicting terminological concepts, is arranged to reflect conceptual proximity among the nodes. The information retrieval system processes the queries, identifies topics related to the query as well as query feedback terms, and then links both the topics and feedback terms to nodes of the knowledge base with corresponding terminological concepts. At least one focal node is selected from the knowledge base based on the topics to determine a conceptual proximity between the focal node and the query feedback nodes. The query feedback terms are ranked based on conceptual proximity to the focal node. A content processing system that identifies themes from a corpus of documents for use in query feedback processing is also disclosed.
A method and system for improving text searching is disclosed. The method and system provides a network of document relationship and utilizes the network of document relationships to identify the region of documents that can be used to satisfy a user's request. In a preferred embodiment, the text searching method in accordance with the present invention augments a conventional text search by using information on document relationships and metadata. The text searching method and system improves upon conventional text search techniques by incorporating relationship metadata to define regions to search within. In the present invention the definition of a region is not limited to just categories as it includes neighborhoods around individual documents and sets which have been user defined.
Method and system for identifying and characterizing publications containing a specified search-phrase, using number of, and relative frequency of, occurrences of the search-phrase (and, optionally, of synonym-phrases) in each publication to develop a measure of significance that represents the relevance of each identified publication (in which the specified search-phrase occurs) to the original search. The measure of significance can also be based on minimum separation distance between search-phrase occurrences and/or upon occurrences of search-phrase synonyms and time intervals within which the publication release dates fall.
A method and system for improving text searching is disclosed. The method and system provides a network of document relationship and utilizes the network of document relationships to identify the region of documents that can be used to satisfy a user's request. In a preferred embodiment, the text searching method in accordance with the present invention augments a conventional text search by using information on document relationships and metadata. The text searching method and system improves upon conventional text search techniques by incorporating relationship metadata to define regions to search within. In the present invention the definition of a region is not limited to just categories as it includes neighborhoods around individual documents and sets which have been user defined.
