Searching text via function learning
First Claim
1. A method for searching documents in a corpus of documents based on a textual search query, the method comprising:
- selecting a program that is characterized by a set of program parameters and which includes a search function and an error evaluation function that evaluates results from the search function, the selected program being structured to receive the textual search query as input and to provide, as output, values from the error evaluation function that indicate the relevance of each document in the corpus to the textual search query;
training the selected program using a machine learning technique based on training data from a subset of the corpus of documents, the machine learning technique comprises (i) applying (a) a structure determination technique that determines a learned structure for the selected program and (b) a program parameter values training technique that determines without user intervention learned values for the program parameters, wherein both the learned structure and the learned values are determined based on the error evaluation function; and
(ii) embodying both the learned structure and the learned values into the selected program to provide a trained program; and
executing the trained program using the textual search query as input.
0 Assignments
0 Petitions
Accused Products
Abstract
A method which does not rely on explicit inverted indices is provided to search for documents in a corpus of documents responsive to a textual search query. The method includes (a) selecting a program that is customized by setting values for a plurality of parameters, the program structured to receive the textual search query as input and to provide as output values indicating the relevance of the documents in the corpus to the search query; (b) training the program using a machine learning technique; and (c) applying the trained program to the textual search query. The program may be based on a structure that is developed based on a genetic programming technique.
8 Citations
9 Claims
-
1. A method for searching documents in a corpus of documents based on a textual search query, the method comprising:
-
selecting a program that is characterized by a set of program parameters and which includes a search function and an error evaluation function that evaluates results from the search function, the selected program being structured to receive the textual search query as input and to provide, as output, values from the error evaluation function that indicate the relevance of each document in the corpus to the textual search query; training the selected program using a machine learning technique based on training data from a subset of the corpus of documents, the machine learning technique comprises (i) applying (a) a structure determination technique that determines a learned structure for the selected program and (b) a program parameter values training technique that determines without user intervention learned values for the program parameters, wherein both the learned structure and the learned values are determined based on the error evaluation function; and
(ii) embodying both the learned structure and the learned values into the selected program to provide a trained program; andexecuting the trained program using the textual search query as input. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
Specification