Determining corresponding terms written in different formats

Abstract

Methods and apparatus consistent with the invention allow a user to submit an ambiguous search query and to receive relevant search results. Queries can be expressed using character sets and/or languages that are different from the character set and/or language of at least some of the data that is to be searched. A translation between these character sets and/or languages can be performed by examining the use of terms in aligned text. Probabilities can be associated with each possible translation. Refinements can be made to these probabilities by examining user interactions with the search results.

What is claimed is: 
     
         1 . A method for creating a probabilistic dictionary, the probabilistic dictionary mapping terms in a first format to terms in a second format, the method comprising:
 for a given term, identifying a first set of data in the first format that contains the term;   identifying a second set of data in the second format that is aligned with the first set of data; and   analyzing the second set of data to determine one or more probabilities with which the given term maps onto one or more terms in the second set of data.   
     
     
         2 . The method of  claim 1 , further comprising:
 adding the given term to the dictionary along with one or more probabilities with which the given term maps onto one or more terms in the second set of data.   
     
     
         3 . The method of  claim 2 , further comprising:
 repeating, for each term to be added to the dictionary, said steps of identifying a first set of data, identifying a second set of data, and analyzing the second set of data.   
     
     
         4 . The method of  claim 1 , in which the first set of data comprises a first set of anchor text pointing to a set of one or more web pages, and in which the second set of data comprises a second set of anchor text pointing to the same set of one or more web pages. 
     
     
         5 . The method of  claim 1 , in which the first set of data comprises a set of text written in a first language, and in which the second set of data comprises the same set of text written in a second language. 
     
     
         6 . The method of  claim 1 , in which the probability with which the given term maps onto a term in the second set of data is calculated by dividing the number of occurrences of the term in the second set of data by the total number of terms in the second set of data. 
     
     
         7 . The method of  claim 1 , further comprising:
 modifying the probability with which the given term maps onto a term in the second set of data based, at least in part, on an analysis of a user's selection of search results.   
     
     
         8 . The method of  claim 1 , further comprising:
 modifying the probability with which the given term maps onto a term in the second set of data based, at least in part, on an analysis of a user's previous queries.   
     
     
         9 . A translation method comprising:
 identifying a first body of text written in a first format;   identifying a second body of text written in a second format, the second body of text being aligned with the first body of text;   creating a dictionary of translations between terms in the first body of text and terms in the second body of text by comparing the occurrence of terms in the first body of text with the occurrence of terms in the second body of text.   
     
     
         10 . A translation method as in  claim 9 , in which the dictionary of translations includes one or more probabilities associated with the translations. 
     
     
         11 . A translation method as in  claim 9 , in which the first format comprises a first character set and the second format comprises a second character set. 
     
     
         12 . A translation method as in  claim 9 , in which the first format comprises a first language and the second format comprises a second language. 
     
     
         13 . A translation method as in  claim 9 , in which the first body of text comprises anchor text and the second body of text comprises anchor text.