Automatic context sensitive language generation, correction and enhancement using an internet corpus

Abstract

A computer-assisted language generation system including sentence retrieval functionality, operative on the basis of an input text containing words, to retrieve from an internet corpus a plurality of sentences containing words which correspond to the words in the input text and sentence generation functionality operative using a plurality of sentences retrieved by the sentence retrieval functionality from the internet corpus to generate at least one correct sentence giving expression to the input text.

1 - 81 . (canceled) 
     
     
         82 . A computer-assisted language generation system comprising:
 sentence retrieval functionality, operative on the basis of an input text containing a plurality of words, to retrieve from an internet corpus a plurality of sentences containing words which correspond to said plurality of words in the input text; and   sentence generation functionality operative using said plurality of sentences to generate at least one correct sentence giving expression to said input text, said sentence generation functionality comprising:
 an alternatives generator, generating on the basis of said plurality of sentences a text-based representation providing multiple alternatives for each of said plurality of words in said input text; 
 a selector for selecting among at least said multiple alternatives for each of said plurality of words in said input text, based at least partly on a relationship between selected ones of said multiple alternatives for at least some of said plurality of words in said language input; and 
 a correction generator operative to provide said at least one correct sentence based on selections made by said selector, said selector being operative to make said selections by carrying out the following functions:
 selection of a first set of words or combinations of words which include less than all of said plurality of words in said input text for an initial selection; and 
 at least one of:
 thereafter ordering elements of said first set of words or combinations of words to establish priority of selection; and 
 thereafter when selecting among said multiple alternatives for an element of said first set of words, choosing other words, but not all, of said plurality of words as a context to influence said selecting. 
 
 
   
     
     
         83 . A system according to  claim 82  and wherein said correction generator comprises a corrected language generator operative to provide said at least one correct sentence based on selections made by said selector without requiring user intervention. 
     
     
         84 . A system according to  claim 82  and wherein said input text is at least one of:
 an output of optical character recognition functionality; 
 an output of machine translation functionality; and 
 an output of word processing functionality. 
 
     
     
         85 . A system according to  claim 82  and wherein said selector is operative to make said selections based on at least two of the following correction functions:
 spelling correction; 
 misused word correction; 
 grammar correction; and 
 vocabulary enhancement. 
 
     
     
         86 . A system according to  claim 85  and wherein said selector is operative to make said selections based on at least one of the following time ordering of corrections:
 spelling correction prior to at least one of misused word correction, grammar correction and vocabulary enhancement; and 
 misused word correction and grammar correction prior to vocabulary enhancement. 
 
     
     
         87 . A system according to  claim 82  and wherein said input text is machine generated from speech and said selector is operative to make said selections based on at least one of the following correction functions:
 misused word correction; 
 grammar correction; and 
 vocabulary enhancement. 
 
     
     
         88 . A computer-assisted language generation system comprising:
 sentence retrieval functionality, operative on the basis of an input text containing a plurality of words, to retrieve from an internet corpus a plurality of sentences containing words which correspond to said plurality of words in the input text; and   sentence generation functionality operative using said plurality of sentences to generate at least one correct sentence giving expression to said input text, said sentence generation functionality comprising:
 an alternatives generator, generating on the basis of said plurality of sentences a text-based representation providing multiple alternatives for each of said plurality of words in said input text; 
 a selector for selecting among at least said multiple alternatives for each of said plurality of words in said input text, based at least partly on a relationship between selected ones of said multiple alternatives for at least some of said plurality of words in said language input; and 
 a correction generator operative to provide said at least one correct sentence based on selections made by said selector, said selector being operative to make said selections by carrying out the following function:
 when selecting for an element having at least two words, evaluating each of said multiple alternatives for each of said at least two words in combination with each of said multiple alternatives for each other of said at least two words. 
 
   
     
     
         89 . A system according to  claim 88  and wherein said correction generator comprises a corrected language generator operative to provide said at least one correct sentence based on selections made by said selector without requiring user intervention. 
     
     
         90 . A system according to  claim 88  and wherein said input text is at least one of:
 an output of optical character recognition functionality; 
 an output of machine translation functionality; and 
 an output of word processing functionality. 
 
     
     
         91 . A system according to  claim 88  and wherein said selector is operative to make said selections based on at least two of the following correction functions:
 spelling correction; 
 misused word correction; 
 grammar correction; and 
 vocabulary enhancement. 
 
     
     
         92 . A system according to  claim 91  and wherein said selector is operative to make said selections based on at least one of the following time ordering of corrections:
 spelling correction prior to at least one of misused word correction, grammar correction and vocabulary enhancement; and 
 misused word correction and grammar correction prior to vocabulary enhancement. 
 
     
     
         93 . A system according to  claim 88  and wherein said input text is machine generated from speech and said selector is operative to make said selections based on at least one of the following correction functions:
 misused word correction; 
 grammar correction; and 
 vocabulary enhancement.