Work Files Saved Searches
   My Account                                                  Search:   Quick/Number   Boolean   Advanced       Help   


 The Delphion Integrated View

  Buy Now:   Buy PDF- 75pp  PDF  |   File History  |   Other choices   
  Tools:  Citation Link  |  Add to Work File:    
  View:  Expand Details   |  INPADOC   |  Jump to: 
 
 Email this to a friend  Email this to a friend 
       
Title: US5510981: Language translation apparatus and method using context-based translation models
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
75 pages

 
Inventor: Berger, Adam L.; New York, NY
Brown, Peter F.; New York, NY
Della Pietra, Stephen A.; Pearl River, NY
Della Pietra, Vincent J.; Blauvelt, NY
Kehler, Andrew S.; Somerville, MA
Mercer, Robert L.; Yorktown Heights, NY

Assignee: International Business Machines Corporation, Armonk, NY
other patents from INTERNATIONAL BUSINESS MACHINES CORPORATION (280070) (approx. 44,393)
 News, Profiles, Stocks and More about this company

Published / Filed: 1996-04-23 / 1993-10-28

Application Number: US1993000144913

IPC Code: Advanced: G06F 17/28;
Core: more...
IPC-7: G06F 17/28;

ECLA Code: G06F17/28D2; G06F17/28D4;

U.S. Class: Current: 704/002; 704/009; 704/231; 704/257; 704/277; 715/236;
Original: 364/419.02; 364/419.08; 364/419.16; 381/043;

Field of Search: 364/419.02,419.08,419.16,200 MS File 381/043,51

Government Interest:     This invention was made with Government support under Contract No. N00014-91-C-0135 awarded by the Office of Naval Research. The Government has certain rights in this invention.

Priority Number:
1993-10-28  US1993000144913

Abstract:     An apparatus for translating a series of source words in a first language to a series of target words in a second language. For an input series of source words, at least two target hypotheses, each including a series of target words, are generated. Each target word has a context comprising at least one other word in the target hypothesis. For each target hypothesis, a language model match score including an estimate of the probability of occurrence of the series of words in the target hypothesis. At least one alignment connecting each source word with at least one target word in the target hypothesis is identified. For each source word and each target hypothesis, a word match score including an estimate of the conditional probability of occurrence of the source word, given the target word in the target hypothesis which is connected to the source word and given the context in the target hypothesis of the target word which is connected to the source word. For each target hypothesis, a translation match score including a combination of the word match scores for the target hypothesis and the source words in the input series of source words. A target hypothesis match score including a combination of the language model match score for the target hypothesis and the translation match score for the target hypothesis. The target hypothesis having the best target hypothesis match score is output.

Attorney, Agent or Firm: Schechter, Marc D. ; Tassinari, Robert P. ;

Primary / Asst. Examiners: Huntley, David M.; Poinvil, Frantzy

Maintenance Status: E3 Expired  Check current status

INPADOC Legal Status: Show legal status actions          Buy Now: Family Legal Status Report

Designated Country: AT BE CH DE ES FR GB IT LI NL SE 

Family: Show 13 known family members

First Claim:
Show all 21 claims
We claim:     1. An apparatus for translating a series of source words in a first language to a series of target words in a second language different from the first language, said apparatus comprising:
  • means for inputting said series of source words;
  • means for generating at least two target hypotheses, each target hypothesis comprising said series of target words selected from a vocabulary of words in the second language, each target word having a context comprising at least one other word in the target hypothesis;
  • means for generating, for each target hypothesis, a language model match score comprising an estimate of the probability of occurrence of the series of words in the target hypothesis;
  • means for identifying at least one alignment between the input series of source words and each target hypothesis, the alignment connecting each source word with at least one target word in the target hypothesis;
  • means for generating, for each source word and each target hypothesis, a word match score comprising an estimate of the conditional probability of occurrence of the source word, given the target word in the target hypothesis which is connected to the source word and given the context of the target word in the target hypothesis which is connected to the source word;
  • means for generating, for each target hypothesis, a translation match score comprising a combination of the word match scores for the target hypothesis and the source words in the input series of source words;
  • means for generating a target hypothesis match score for each target hypothesis, each target hypothesis match score comprising a combination of the language model match score for the target hypothesis and the translation match score for the target hypothesis; and
  • means for outputting the target hypothesis having the best target hypothesis match score.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 125 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (125)   |   Backward references (8)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 22pp US4754489  1988-06 Bokder  The Palantir Corporation Means for resolving ambiguities in text based upon character context
Get PDF - 12pp US4829580  1989-05 Church  Telephone and Telegraph Company, AT&T Bell Laboratories Text analysis system with letter sequence recognition and speech stress assignment arrangement
Get PDF - 23pp US4882759  1989-11 Bahl et al.  International Business Machines Corporation Synthesizing word baseforms used in speech recognition
Get PDF - 31pp US5033087  1991-07 Bahl et al.  International Business Machines Corp. Method and apparatus for the automatic determination of phonological rules as for a continuous speech recognition system
Get PDF - 65pp US5068789  1991-11 Van Vliembergen  OCE-Nederland B.V. Method and means for grammatically processing a natural language sentence
Get PDF - 21pp US5109509  1992-04 Katayama et al.  Hitachi, Ltd. System for processing natural language including identifying grammatical rule and semantic concept of an undefined word
Get PDF - 12pp US5146405  1992-09 Church  AT&T Bell Laboratories Methods for part-of-speech determination and usage
Get PDF - 56pp US5200893  1993-04 Dzawa et al.  Hitachi, Ltd. Computer aided text generation method and system
       
Foreign References: None

Other Abstract Info: DERABS G1995-163666

Other References:
  • Brown, P. F., et al. "Analysis, Statistical Transfer, and Synthesis in Machine Translation." Proceedings of the Fourth International Conference on Theoretical and Methodological Issues in Machine Translation, Nov. 1992, pp. 83-100.
  • Brown, Peter F., et al. "Class-Based N-Gram Models of Natural Language." Computational Linguistics, vol. 18, No. 4, Dec. 1992, pp. 467-480.
  • Brown, Peter F., et al. "The Mathematics of Statistical Machine Translation: Parameter Estimation." Computational Linguistics, vol. 19, No. 2, Jun. 1993, pp. 263-311.
  • Brown, Peter F., et al. "Method and Apparatus For Natural Language Translation." U.S. patent application Ser. No. 07/736,278, filed Jul. 25, 1991.
  • Brown, P. F. et al. "Word Sense Disambiguation Using Statistical Methods." Proceedings 29th Annual Meeting of the Association for Computational Linguistics, Berkeley, California, Jun. 1991, pp. 265-270.
  • Darroch, J. N. et al. "Generalized Iterative Scaling for Log-Linear Models." The Annals of Mathematical Statistics, vol. 43, No. 5, 1972, pp. 1470-1480. Cited by 6 patents


  • Inquire Regarding Licensing

    Powered by Verity


    Plaques from Patent Awards      Gallery of Obscure PatentsNominate this for the Gallery...

    Thomson Reuters Copyright © 1997-2014 Thomson Reuters 
    Subscriptions  |  Web Seminars  |  Privacy  |  Terms & Conditions  |  Site Map  |  Contact Us  |  Help