Method and apparatus for deriving logical relations from linguistic relations with multiple relevance ranking strategies for information retrieval

• US 7,249,127 B2
• Filed: 04/28/2004
• Issued: 07/24/2007
• Est. Priority Date: 05/24/2001
• Status: Expired due to Term

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Microsoft Corporation
• Inventors: Azzam, Saliha
• Primary Examiner(s): Wong; Leslie
• Application Number:
  US10/834,303
• Publication Number:
  US 20040205079A1
• Time in Patent Office: 1,182 Days
• Field of Search: 707/2, 707/4, 707/102, 707/104.1
• US Class Current: 707/772
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: Y10S 707/922 Communications
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method and apparatus are provided for improving the precision of information retrieval systems that use logical form searching techniques. Under one embodiment of the invention, several logical form triples are produced from the user'"'"'s query and are combined together by restrictive logical operators to generate a compound logical form query. A search is then performed to find documents that meet the requirements set by the compound logical form query. In other embodiments, results generated by a logical form search are intersected with results from a word search to form a more precise set of results.

Claims

1. A method for retrieving information from a document collection, the method comprising:

converting a user query into at least two logical form triples;

generating a compound logical form query by connecting at least two of the logical form triples with a restrictive operator wherein generating compound logical form query comprises;

determining a score for each logical form triple;

combining the scores for each logical form triple to form a total score; and

generating the compound logical form query based in art on the total score; and

searching an index of the document collection for documents that match the compound logical form query.

2. The method of claim 1 wherein searching an index comprises searching a field in the index that contains entire logical form triples.

3. The method of claim 1 wherein converting a user query comprises identifying a query type from the user query and generating a logical form triple based on the query type.

4. The method of claim 1 wherein determining a score for each logical form triple comprises determining a score based on properties of words associated with a logical form triple.

5. The method of claim 1 wherein determining a score for a logical form triple comprises determining a score based on a linguistic type associated with the logical form triple.

6. The method of claim 1 wherein generating the compound logical form query based in part on the total score comprises:

determining that the total score is relatively low; and

based on the relatively low total score, using restrictive operators between each logical form triple in the compound logical form query.

7. The method of claim 1 wherein generating the compound logical form query based in part on the total score comprises:

determining that the total score is relatively high; and

based on the relatively high total score, constructing the compound logical form query to allow fuzzy matching of at least one logical form triple.

9. The method of claim 1 wherein generating the compound logical form query based in part on the total score comprises:

determining that the total score is relatively high; and

based on the relatively high total score, constructing the compound logical form query using only some of the logical form triples formed from the user query.

10. The method of claim 1 wherein searching the index produces a set of logical-based search results and wherein the method of retrieving information further comprises:

searching a word index of the document collection for documents that match words in the user query to produce a set of word-based search results; and

intersecting the logical-based search results with the word-based search results to form a filtered set of search results.

8. The method of claim l wherein generating the compound logical form query based in part on the total score comprises:

determining that the total score is relatively high; and

based on the relatively high total score, placing a non-restrictive operator between at least two logical form triples in the compound logical form query.

11. A method of retrieving information from a document collection, the method comprising:

generating a compound logical form query from a user query, the compound logical form query having at least two logical form triples connected by a restrictive operator, wherein generating a compound logical form query comprises;

determining the restrictiveness of a set of logical form triples identified from the user query by weighting each individual logical form triple in the set of logical form triples; and

combining logical form triples based on the weightings of the logical form triples to form the compound logical form query so as to limit the restrictiveness of the compound logical form query formed from the set of logical form triples;

applying the compound logical form query to a logical form triple index of a document collection to form a set of logic-based search results;

generating a word query based on words in the user query;

applying the word query to a word index of the document collection to form a set of word-based search results; and

intersecting the logic-based search results with the word-based search results to form a set of filtered compound results.

12. The method of claim 11 wherein generating a word query comprises identifying important words in the user query and placing the important words in the word query.

13. A computer-readable storage medium having computer-executable instructions for performing information retrieval steps comprising:

performing a logic-based search of a document collection using logical form triples created from a user query to create logic-based search results, performing the logic-based search comprising forming a compound logical form query by identifying at least two logical form triples from the user query, weighting each of the logical form triples with weights, summing the weights to form a score and connecting at least two of the logical form triples with a restrictive operator based on the score, and using the compound logical form query to search the document collection;

performing a word-based search of the document collection using words taken from the user query to create word-based search results; and

intersecting the logic-based search results and the word-based search results to form filtered search results.

14. The computer-readable storage medium of claim 13 wherein performing a word-based search comprises identifying important words in the user query and using only the important words in the word-based search.