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

• US 9,026,432 B2
• Filed: 12/30/2013
• Issued: 05/05/2015
• Est. Priority Date: 08/01/2007
• Status: Active Grant

• Current Assignee: Ginger Software, Inc.
• Original Assignee: Ginger Software, Inc.
• Inventors: Zangvil, Yael Karov
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US14/143,827
• Publication Number:
  US 20140122062A1
• Time in Patent Office: 491 Days
• Field of Search: 704 1- 10
• US Class Current: 704/9
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

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.

Claims

1. A computer-assisted language generation system comprising:

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 said 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 the input text,

said sentence generation functionality comprising;

sentence simplification functionality operative to simplify said sentences retrieved from said internet corpus;

simplified sentence grouping functionality for grouping similar simplified sentences provided by said sentence simplification functionality;

simplified sentence group ranking functionality for ranking groups of said similar simplified sentences; and

sentence selection functionality operative to select at least one of said similar simplified sentences as said at least one correct sentence based on said ranking;

said simplified sentence group ranking functionality operates using

an extent to which the group includes words which do not correspond to the words in an independent phrase and their alternatives.

2. A computer-assisted language generation system according to claim 1 and wherein said sentence retrieval functionality comprises:

an independent phrase generator splitting said input text into one or more independent phrases;

a word stein generator and classifier, operative for each independent phrase to generate word stems for words appearing therein and to assign importance weights thereto; and

an alternatives generator for generating alternative word sterns corresponding to said word stems.

3. A computer-assisted language generation system according to claim 2 and also comprising a stein to sentence index which interacts with said internee corpus for retrieving said plurality of sentences containing words which correspond to said words in the input text.

4. A computer-assisted language generation system according to claim 1 and wherein said simplified sentence group ranking functionality also uses the number of simplified sentences contained in a group.

5. A computer-assisted language generation system according to claim 1 and wherein said simplified sentence group ranking functionality also uses the degree to which the word stems of the words in the group correspond to the word stems in an independent phrase and their alternatives.

6. A computer-assisted language generation system according to claim 1 and viterein said simplified sentence group ranking functionality includes defining the weight of a word stem, to indicate the importance of the word in the language.

7. A computer-assisted language generation system according to claim 1 and wherein said simplified sentence group ranking functionality includes calculating a Positive Match Rank corresponding to a degree to which the word stems of the words in the group correspond to the word stems in an independent phrase and their alternatives.

8. A computer-assisted language generation system according to claim 1 and wherein said simplified sentence group ranking functionality includes calculating a Negative Match Rank corresponding to said extent to which the group includes words which do not correspond to the words in the independent phrase and their alternatives.

9. A computer-assisted language generation system according to claim 1 and wherein said simplified sentence group ranking functionality includes calculating a Composite Rank based on:

a number of simplified sentences contained in a group;

a Positive Match Rank corresponding to a degree to which the word stems of the words in the group correspond to the word stems in an independent phrase and their alternatives; and

a Negative Match Rank corresponding to said extent to which the group includes words which do not correspond to the words in the independent phrase and their alternatives.

10. A computer-assisted language generation system according to claim 1 and also comprising machine translation functionality providing said input text.

11. A computer assisted language generation system according to claim 1 and also comprising text correction functionality providing said input text.

12. A computer-assisted language generation system according to claim 1 and also comprising sentence search functionality providing said input text based on user-entered query words.

13. A computer-assisted language generation system according to claim 1 and also comprising speech-to-text conversion functionality providing said input text.