Automatic context sensitive language correction and enhancement using an internet corpus

• US 8,914,278 B2
• Filed: 07/31/2008
• Issued: 12/16/2014
• Est. Priority Date: 08/01/2007
• Status: Active Grant

• Current Assignee: Ginger Software, Inc.
• Original Assignee: Ginger Software, Inc.
• Inventors: Zangvil, Yael Karov, Zangvil, Avner
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): Sirjani, Fariba
• Application Number:
  US12/669,175
• Publication Number:
  US 20100286979A1
• Time in Patent Office: 2,329 Days
• Field of Search: 704/9
• 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 correction system including spelling correction functionality, misused word correction functionality, grammar correction functionality and vocabulary enhancement functionality utilizing contextual feature-sequence functionality employing an internet corpus.

Claims

1. A computer-assisted language correction system comprising:

a computer storage device, storing computer modules;

a computer processor operative to execute said modules;

said computer modules including;

contextual feature-sequence (CFS) functionality operative to generate a plurality of contextual feature-sequences based on an input sentence, said contextual feature sequence comprising at least one of N-grams, skip-grams, switch-grams, co-occurrences, and combinations thereof;

an alternatives generator, generating on the basis of said input sentence a text-based representation providing multiple alternatives for each of a plurality of words in the sentence, said multiple alternatives including non-contextual corrections for each of said plurality of words;

a selector for selecting among at least said multiple alternatives for each of said plurality of words in the sentence, said selector including context based scoring functionality operative to rank said multiple alternatives, based at least partly on contextual feature-sequence frequencies of occurrences in an internet corpus for each of the plurality of contextual feature-sequences, said context based scoring functionality including ranking said multiple alternatives based at least partially on a CFS importance score, wherein the CFS importance score is a function of a combination of;

a) a number of parsing tree nodes that correspond to a same part of the CFS, and b) a frequency of occurrence of each of the words in the CFS; and

a correction generator operative to provide a correction output based on selections made by said selector.

2. A computer-assisted language correction system according to claim 1 wherein said selector is operative to make said selections based on at least one of the following correction functions:

spelling correction;

misused word correction;

grammar correction; and

vocabulary enhancement.

3. A computer-assisted language correction system according to claim 1 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.

4. A computer-assisted language correction system according to claim 3 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.

5. A computer-assisted language correction system according to claim 2 and wherein:

said input sentence is provided by one of the following functionalities;

word processor functionality;

machine translation functionality;

speech-to-text conversion functionality;

optical character recognition functionality; and

instant messaging functionality; 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.

6. A computer-assisted language correction system according to claim 2 and wherein said correction generator comprises a corrected language input generator operative to provide a corrected language output based on selections made by said selector without requiring user intervention.

7. A computer-assisted language correction system according to claim 2 and wherein said grammar correction functionality includes at least one of punctuation, verb inflection, single/plural, article and preposition correction functionalities.

8. A computer-assisted language correction system according to claim 2 and wherein said grammar correction functionality includes at least one of replacement, insertion and omission correction functionalities.

9. A computer-assisted language correction system according to claim 1 and wherein said context based scoring functionality is also operative to rank said multiple alternatives based at least partially on normalized CFS frequencies of occurrences in said internet corpus.

10. A computer-assisted language correction system according to claim 1 and wherein said CFS importance score is additionally a function of at least one of the following:

a CFS length and a CFS type.

11. A computer-assisted language correction system according to claim 1 and wherein said CFS importance score is additionally a function of all of the following:

a CFS length and a CFS type.