Natural language information retrieval system and method

A method of operating a computerized information retrieval system where information is retrieved from a database containing documents in response to user queries, the method comprising the steps of:

• receiving a natural language query specifying information to be retrieved;
• generating an alternative representation of the query that includes a plurality of different individual representations of the query;
• defining a plurality of evidence sources based on the different individual representations of the query;
• for each document, determining similarity scores for each evidence source in the plurality of evidence sources, and combining the plurality of similarity scores for that document using a regression formula to determine a measure of relevance;
• and
• providing a set of documents that satisfy a retrieval criterion based on the measures of relevance of the documents.

A method of operating a computerized information retrieval system where information is retrieved from a database containing documents in response to user queries, the method comprising the steps of:

• receiving a natural language query specifying information to be retrieved;
• extracting terms that appear in the query;
• detecting words that indicate multi-part proper nouns in the query;
• if a word indicates that two proper nouns around the word is in fact one name, determining the boundary of each name which consists of one or more proper nouns;
• classifying the boundary determined proper nouns into one category from a plurality of pre-determined conceptual categories, including determining the one category using information revealed by noun phrases in close proximity to the boundary determined proper nouns;
• converting the classified proper noun into a commonly recognized standard form;
• generating an alternative representation of the query that includes both the category which is assigned to the proper noun and the standard form of the proper noun in the query;
• processing documents in the database to tag the documents for proper nouns;
• matching the alternative representation of the query against the database by determining a measure of relevance for each document;
• and
• providing a set of documents that satisfy a retrieval criterion.