Natural language information retrieval system and method
First Claim
1. 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;
detecting evidence sources from the query;
determining discourse aspects, such as temporal information or intention information, based on the detected evidence sources;
generating a score for each of the determined discourse aspects using a statistical evidence combination method;
generating an alternative representation of the query based on the discourse aspects whose scores exceed a predetermined threshold score;
processing documents in the database to tag such documents for such discourse aspects;
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.
1 Assignment
0 Petitions
Accused Products
Abstract
Techniques for generating sophisticated representations of the contents of both queries and documents in a retrieval system by using natural language processing (NLP) techniques to represent, index, and retrieve texts at the multiple levels (e.g., the morphological, lexical, syntactic, semantic, discourse, and pragmatic levels) at which humans construe meaning in writing. The user enters a query and the system processes the query to generate an alternative representation, which includes conceptual-level abstraction and representations based on complex nominals (CNs), proper nouns (PNs), single terms, text structure, and logical make-up of the query, including mandatory terms. After processing the query, the system displays query information to the user, indicating the system'"'"'s interpretation and representation of the content of the query. The user is then given an opportunity to provide input, in response to which the system modifies the alternative representation of the query. Once the user has provided desired input, the possibly modified representation of the query is matched to the relevant document database, and measures of relevance generated for the documents. A set of documents is presented to the user, who is given an opportunity to select some or all of the documents, typically on the basis of such documents being of particular relevance. The user then initiates the generation of a query representation based on the alternative representations of the selected document(s).
-
Citations
6 Claims
-
1. 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; detecting evidence sources from the query; determining discourse aspects, such as temporal information or intention information, based on the detected evidence sources; generating a score for each of the determined discourse aspects using a statistical evidence combination method; generating an alternative representation of the query based on the discourse aspects whose scores exceed a predetermined threshold score; processing documents in the database to tag such documents for such discourse aspects; 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. - View Dependent Claims (2)
-
-
3. 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. - View Dependent Claims (4, 5)
-
-
6. 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.
-
Specification