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


 The Delphion Integrated View

  Buy Now:   Buy PDF- 45pp  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: US6304841: Automatic construction of conditional exponential models from elementary features
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
45 pages

 
Inventor: Berger, Adam Lee; New York, NY
Brown, Peter Fitzhugh; New York, NY
Della Pietra, Stephen Andrew; Valley Cottage, NY
Della Pietra, Vincent Joseph; Blauvelt, NY
Lafferty, John David; Pittsburgh, PA
Mercer, Robert Leroy; Mt. Sinai, 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: 2001-10-16 / 1997-07-29

Application Number: US1997000902177

IPC Code: Advanced: G06F 17/27; G06F 17/28;
Core: more...
IPC-7: G06F 17/27;

ECLA Code: G06F17/27R2; G06F17/28D2;

U.S. Class: Current: 704/002;
Original: 704/002; 705/001;

Field of Search: 705/001-10,257 704/2;9

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:
1997-07-29  US1997000902177
1995-05-01  US1995000431597
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 comprising 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 comprises 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 comprises 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 comprises a combination of the word match scores for the target hypothesis and the source words in the input series of source words.

Attorney, Agent or Firm: F. Chau & Associates, LLP ;

Primary / Asst. Examiners: Poinvil, Frantzy;

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

       
Related Applications:
Application Number Filed Patent Pub. Date  Title
US1995000431597 1995-05-01       
US1993000144913 1993-10-28    1996-04-23  Language translation apparatus and method using context-based translation models


       
Parent Case:     This invention is a continuation of U.S. patent application Ser. No. 08/431,597 filed May 1, 1995 now abandoned, which is a continuation-in-part of U.S. patent application Ser. No. 08/144,913, filed Oct. 28, 1993, now U.S. Pat. No. 5,510,981, issued Apr. 23, 1996.

Designated Country: BE CH FR GB IT LI NL SE 

Family: Show 13 known family members

First Claim:
Show all 10 claims
What we claim as new, and wish to secure by Letters Patent, is:     1. A computer-implemented method for translating source words using a language translation process, the language translation process using an adjustable model, the method comprising the steps of:
  • choosing an initial model for the language translation process;
  • generating, responsive to the source words, an output corresponding to at least one target hypothesis using the language translation process and the initial model;
  • adjusting the initial model to generate an adjusted model, including the following steps (a)-(j):
    • (a) providing a set of candidate features exhibited in the output of the language translation process;
    • (b) providing a sample of data representing the output of the language translation process being modeled;
    • (c) generating an intermediate model from the initial model of the language translation process;
    • (d) initializing an active set S of features contained in the intermediate model;
    • (e) computing scores representing the benefit of adding features to the intermediate model;
    • (f) selecting one or more features having scores higher than a first given value;
    • (g) if none of the scores is higher than a second given value, stop;
    • (h) adding selected features to the set S of active features;
    • (i) computing a model Ps containing the features in S to be the intermediate model; and
    • (j) repeating steps (e)-(i) until the stop condition of step (g) is satisfied to determine from the intermediate model an adjusted model; and
  • translating the source words with the language translation process operating using the adjusted model.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 60 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (60)   |   Backward references (2)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 95pp US4974191  1990-11 Amirghodsi et al.  Syntellect Software Inc. Adaptive natural language computer interface system
Get PDF - 75pp US5510981  1996-04 Berger et al.  International Business Machines Corporation Language translation apparatus and method using context-based translation models
       
Foreign References:
Buy
PDF
Publication Date IPC Code Assignee   Title
Get PDF - 161pp EP0525470A2 1993-02  G06F 15/38 INTERNATIONAL BUSINESS MACHINES CORPORATION Method and system for natural language translation 
Get PDF - 38pp EP0568319A2 1993-11  G06F 15/38 SHARP KABUSHIKI KAISHA Machine translation system 


Other Abstract Info: DERABS G1995-163666 DERABS G1996-487513

Other References:
  • David T. Brown, "A Note on Approximations to Discrete Probability Distributions", Information and Control, vol. 2, pp. 386-392 (1959).
  • Brown et al., "The Mathematics of Statistical Machine Translation: Parameter Estimation", Computational Linguistics, vol. 19, No.2, pp. 263-311.
  • I. Csiszar, "I-Divergence Geometry of Probability Distributions and Minimization Problems", The Annals of Probability, 1975, vol. 3, No. 1, pp. 146-158. (13 pages)
  • J.N. Darroch et al., "Generalized Iterative Scaling for Log-Linear Models", The Annals of Mathematical Statistics, 1972, vol. 43, No. 5, pp. 1470-1480. Cited by 6 patents
  • I. Csiszar, "A Geometric Interpretation of Darroch and Ratcliff s Generalized Iterative Scaling", The Annals of Statistics, 1989, vol. 17, No. 3, pp. 1409-1412. (5 pages)
  • Eurospeech 89, European Conference on Speech Communication and Technology, "A Massively Parallel Model of Speech-To-Speech Dialog Translation: A Step Toward Interpreting Telephony" by H. Kitano et al., Center for Machine Translation, Carnegie Mellon University, Pennsylvania, vol. 1, pp. 198-201. Editors: J.P. Tubach, et al. (Sep. 1989).
  • Research Report, A Maximm Entropy Approach to Natural Language Processing, Adam L. Berger, et al., IBM Research Division, Yorktown Heights, NY, Aug. 5, 1994.


  • 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