Method and system for retrieving information using natural language queries

• US 20020152202A1
• Filed: 08/24/2001
• Published: 10/17/2002
• Est. Priority Date: 08/30/2000
• Status: Abandoned Application

• Current Assignee: Source Networks Incorporated
• Original Assignee: Source Networks Incorporated
• Inventors: Perro, David J., Li, Po Chuen, Perro, Daniel J., Hedlund, Ric
• Application Number:
  US09/938,879
• Publication Number:
  US 20020152202A1
• Time in Patent Office: Days
• US Class Current: 707/3
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G06F 16/3344 using natural language analysis

Abstract

The present invention provides more accurate natural language searching capabilities by generating contextual phrases that are representative of the key words in a given query and uses those key contextual phrases to locate relevant documents through a search engine or database management system. The present invention generates such contextual phrases by first tagging the text using tagging assumptions and learning methods derived from the comparison of a domain specific and naively annotated corpus. Once tagged, the system then applies matrix rules to the tagged text to create a structural representation of the text. After the generation of the structural representation of the text, the system then applies phrase generation rules, which identify the relationships of the values in the matrix and from those relationships builds a concept phrase table that represents a pattern of contextual phrases derived from the query request. The system then formats the contextual phrases for submission to a DBMS or search engine.

Claims

1. A method for interpreting a natural language query, comprising:

providing a contextual lexicon and contextual rules;

receiving the natural language query, the natural language query having a plurality of text;

tagging the plurality of text using the contextual lexicon and contextual rules;

creating a structural representation of the plurality of text using a plurality of matrix rules;

generating a plurality of conceptual phrases to be submitted to an application for interpreting the plurality of conceptual phrases using a plurality of phrase generation rules applied to the structural representation of the plurality of text.

2. The method of claim 1, further comprising the steps of:

formatting the plurality of concept phrases contained in a the concept phrase table to be understood by a search engine or database management systems application, the formatting step creating a formatted concept phrase; and

submitting the formatted concept phrase to the search engine or database management system to extract information relevant to the concept phrase.

3. The method of claim 1, further comprising the steps of:

formatting the plurality of concept phrases contained in a the concept phrase table to be understood by a search engine or database management systems application, the formatting step creating a formatted concept phrase;

submitting the formatted concept phrase to the search engine or database management system to obtain extracted information relevant to the concept phrase;

obtaining the extracted information from the search engine or database management system;

generating a plurality of second concept phrases from the extracted information for comparison to the plurality of concept phrases;

comparing the plurality of second concept phrases to the plurality of concept phrases; and

ranking the extracted information in order of relevance based on the comparing step.

4. A computer readable storage medium having a computer program stored thereon for processing natural language queries, that, when loaded on a computer, the computer program causing the computer to perform a method for interpreting a natural language query, the method comprising:

providing a contextual lexicon and contextual rules;

receiving the natural language query, the natural language query having a plurality of text;

tagging the plurality of text using the contextual lexicon and contextual rules;

creating a structural representation of the plurality of text using a plurality of matrix rules;

generating a plurality of conceptual phrases to be submitted to an application for interpreting the plurality of conceptual phrases using a plurality of phrase generation rules applied to the structural representation of the plurality of text.