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

 The Delphion Integrated View

  Buy Now:   Buy PDF- 104pp  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: US5805832: System for parametric text to text language translation
[ Derwent Title ]

Country: US United States of America

View Images High


104 pages

Inventor: Brown, Peter Fitzhugh; New York, NY
Cocke, John; Bedford, NY
Della Pietra, Stephen Andrew; Pearl River, NY
Della Pietra, Vincent Joseph; Blauvelt, NY
Jelinek, Frederick; Briarcliff Manor, NY
Lai, Jennifer Ceil; Garrison, NY
Mercer, Robert Leroy; 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: 1998-09-08 / 1995-06-02

Application Number: US1995000459454

IPC Code: Advanced: G06F 17/27; G06F 17/28; G10L 15/00; G10L 15/14;
Core: more...
IPC-7: G06F 17/28;

ECLA Code: G06F17/27M; G06F17/28D2; G06F17/28D8; G06F17/28R;

U.S. Class: Current: 711/001; 704/001; 704/002; 704/009;
Original: 395/752; 395/751; 395/759;

Field of Search: 364/419.02,419.1,419.01,419.08 395/2.49,2.86,751,752,759

Priority Number:
1995-06-02  US1995000459454
1991-07-25  US1991000736278

Abstract:     The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language. The system can either run in batch mode, in which case it translates source-language text into a target language without human assistance, or it can function as an aid to a human translator. When functioning as an aid to a human translator, the human may simply select from the various translation hypotheses provided by the system, or he may optionally provide hints or constraints on how to perform one or more of the stages of source transduction, hypothesis generation and target transduction.

Attorney, Agent or Firm: Tassinari, Esq., Robert P.Sterne, Kessler, Goldstein & Fox P.L.L.C. ;

Primary / Asst. Examiners: Hayes, Gail O.; Hughet, William

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

Related Applications:
Application Number Filed Patent Pub. Date  Title
US1991000736278 1991-07-25    1995-12-19  Method and system for natural language translation

Parent Case:     This application is a continuation of application Ser. No. 07/736,278, filed Jul. 25, 1991, now U.S. Pat. No. 5,477,451.

Designated Country: DE FR GB IT 

Family: Show 10 known family members

First Claim:
Show all 24 claims
Having thus described our invention, what we claim as new and desire to secure by Letters Patent is:     1. A text-to-text language translation system, comprising:
  • a computer processor;
  • a memory having stored therein a plurality of models, wherein said models are used in text-to-text translation, said plurality of models including:
    • a parametric translation model for generating a modeled translation probability, wherein said parametric translation model is generated with reference to a translation model source training text and a translation model target training text, said parametric translation model including a first specification of parameters, and
    • a parametric language model for generating a modeled probability, wherein said parametric language model is generated with reference to a language model training text, said parametric language model including a second specification of parameters; and
  • means for performing text-to-text language translation using said parametric translation model and said parametric language model.

Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 138 U.S. patent(s) that reference this one

U.S. References: Go to Result Set: All U.S. references   |  Forward references (138)   |   Backward references (11)   |   Citation Link

Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 22pp US4754489  1988-06 Bukser  The Palantir Corporation Means for resolving ambiguities in text based upon character context
Get PDF - 10pp US4852173  1989-07 Bahl et al.  International Business Machines Corporation Design and construction of a binary-tree system for language modelling
Get PDF - 13pp US4879580  1989-11 Church  Ricoh Company, Ltd. Image processing apparatus
Get PDF - 23pp US4882759  1989-11 Bahl et al.  International Business Machines Corporation Synthesizing word baseforms used in speech recognition
Get PDF - 12pp US4984178  1991-01 Hemphill et al.  Texas Instruments Incorporated Chart parser for stochastic unification grammar
Get PDF - 19pp US4991094  1991-02 Fagen et al.  International Business Machines Corporation Method for language-independent text tokenization using a character categorization
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 Katayana 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 Ozawa et al.  Hitachi, Ltd. Computer aided text generation method and system
Foreign References:
Publication Date IPC Code Assignee   Title
Get PDF - 15pp EP0327266 1989-08  G06F 15/38 AMERICAN TELEPHONE & TELEGRAPH Method for part-of-speech determination and usage 
Get PDF - 11pp EP0357344 1990-03  G06F 15/38 SHARP KABUSHIKI KAISHA Computer assisted language translating machine 
Get PDF - 17pp EP0399533 1990-11  G06F 15/38 KABUSHIKI KAISHA TOSHIBA Machine translation system and method of machine translation 

Other Abstract Info: DERABS G1993-037875

Other References:
  • Information System & Electronic Development Laboratory Mitsubishi Electr. Corp. "Training of Lexical Models Based on DTW-Based Parameter Reestimation Algorithm" Y. Abe et al, 1988, pp. 623-626.
  • CIIAM 86, Proceedings of the 2nd International Conference on Artificial Intelligence, "Logic Programming for Speech Understanding," pp. 487-497, Abstract of Article, Snyers D. et al.
  • J. Baker, "Trainable Grammars For Speech Recognition", Speech Communications Papers Presented at the 97th Meeting of the Acoustic Society of America, 1979, pp. 547-550.
  • M.E. Lesk, "Lex-A Lexical Analyzer Generator", Computer Science Technical Report, No. 39, Bell Laboratories, Oct. 1975.
  • L. Baum, "An Inequality and Associated Maximation Technique in Statistical Estimation for Probalistic Functions of Markov Processes", Inequalities, vol. 3, 1972, pp. 1-8.
  • F. Jelinek, "Self Organized Language Modeling For Speech Recognition", Language Processing For Speech Recognition, pp. 450-506.
  • Catizone et al., "Deriving Translation Data From Bilingual Texts", Proceedings of the First International Acquisition Workshop, Detroit, Michigan, 1989.
  • J. Spohrer et al., "Partial Traceback in Continuous Speech Recognition", Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Paris, France, 1982.
  • F. Jelinek, R. Mercer, "Interpolated Estimated of Markov Source Parameters From Sparse Data", Workshop on Pattern Recognition in Practice, Amsterdam (Netherland), North Holland, May 21-23, 1980.
  • M. Kay, "Making Connections", ACH/ALLC '91, Tempe, Arizona, 1991, p. 1.
  • "Method For Inferring Lexical Associations From Textual Co-Occurrences", IBM Technical Disclosure Bulletin, vol. 33, Jun. 1990.
  • L. Bahl et al., "A Tree-Based Statistical Language Model For Natural Language Speech Recognition", IEEE Transactions of Acoustics, vol. 37, No. 7, Jul. 1989, pp. 1001-1008. (8 pages) Cited by 7 patents
  • P. Brown, "Word-Sense Disambiguation Using Statistical Methods", Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, Jun. 1991, pp. 264-270.
  • P. Brown et al., "Aligning Sentences in Parallel Corpora", Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, Jun. 1991, pp. 169-176.
  • B. Merialdo, "Tagging Text With A Probalistic Model", Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Paris, France, May 14-17, 1991.

  • 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