Microsoft Technology Licensing, LLC

John J Messerly

William B Dolan

Stephen D Richardson

George E Heidorn

Karen Jensen

The present invention is directed to performing information retrieval utilizing semantic representation of text. In a preferred embodiment, a tokenizer generates from an input string information retrieval tokens that characterize the semantic relationship expressed in the input string. The tokenizer first creates from the input string a primary logical form characterizing a semantic relationship between selected words in the input string. The tokenizer then identifies hypemyms that each have an &ldquo;is a&rdquo; relationship with one of the selected words in the input string. The tokenizer then constructs from the primary logical form one or more alternative logical forms. The tokenizer constructs each alternative logical form by, for each of one or more of the selected words in the input string, replacing the selected word in the primary logical form with an identified hypernym of the selected word. Finally, the tokenizer generates tokens representing both the primary logical form and the alternative logical forms. The tokenizer is preferably used to generate tokens for both constructing an index representing target documents and processing a query against that index.

Information retrieval utilizing semantic representation of text and based on constrained expansion of query words

The present invention is directed to performing information retrieval utilizing semantic representation of text. In a preferred embodiment, a tokenizer generates from an input string information retrieval tokens that characterize the semantic relationship expressed in the input string. The tokenizer first creates from the input string a primary logical form characterizing a semantic relationship between selected words in the input string. The tokenizer then identifies hypernyms that each have an 'is a' relationship with one of the selected words in the input string. The tokenizer then constructs from the primary logical form one or more alternative logical forms. The tokenizer constructs each alternative logical form by, for each of one or more of the selected words in the input string, replacing the selected word in the primary logical form with an identified hypernym of the selected word. Finally, the tokenizer generates tokens representing both the primary logical form and the alternative logical forms. The tokenizer is preferably used to generate tokens for both constructing an index representing target documents and processing a query against that index.

Information retrieval utilizing semantic representation of text by

Information retrieval utilizing semantic representation of text

Weights are assigned to features of data objects and the weights are utilized to determine whether data objects are substantially identical or not. One application of such weights is to assign weights to terms in web page documents. The weights assigned to the terms may then be utilized to determine whether web page documents are substantially identical. A set of identicals may be generated for each web page that is indexed by the system and utilized to repair broken hyperlinks. Specifically, when a uniform resource locator (URL) associated with the hyperlink cannot be resolved or cannot be resolved in a timely fashion, one of the identicals of the desired web page documents may be returned to provide a requesting party with the desired content.

Growing community of inventors

Bainbridge Island, WA, United States of America

John J Messerly