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


 The Delphion Integrated View

  Buy Now:   Buy PDF- 6pp  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: US5987404: Statistical natural language understanding using hidden clumpings
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
6 pages

 
Inventor: Della Pietra, Stephen Andrew; Smithtown, NY
Epstein, Mark Edward; Katonah, NY
Franz, Martin; White Plains, NY
Koppelman, Joshua David Sherer; Austin, TX
Roukos, Salim Estephan; Scarsdale, NY
Ward, Robert Todd; Croton-on-Hudson, 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: 1999-11-16 / 1996-01-29

Application Number: US1996000593032

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

ECLA Code: G06F17/27S; G06F17/28U;

U.S. Class: Current: 704/009; 704/002;
Original: 704/009; 704/002;

Field of Search: 704/001,8,9,257,277

Priority Number:
1996-01-29  US1996000593032

Abstract:     The invention proposes using statistical methods to do natural language understanding. The key notion is that there are "strings" of words in the natural language, that correspond to a single semantic concept. One can then define an alignment between an entire semantic meaning (consisting of a set of semantic concepts), and the English. This is modeled using P(E,A|S). One can model p(S) separately. This allows each parameter to be modeled using many different statistical models.

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

Primary / Asst. Examiners: Isen, Forester W.; Edouard, Patrick N.

Maintenance Status: E2 Expired  Check current status

INPADOC Legal Status: Show legal status actions

Family: None

First Claim:
Show all 12 claims
We claim:     1. A method for performing natural language understanding, comprising:
  • a training phase, comprising:
    • providing a first sentence E of a given language;
    • providing the meaning S of sentence E;
    • generating a translation model by summing a probability of correctness over one or more possible alignments and clumpings between sentence E and meaning S, wherein the actual alignment and clumping are not known, to produce the probabilities of the translation model's parameters;
    • producing the probability distributions of the alignment and storing the probability distributions;
  • an understanding phase, comprising:
    • inputting a second sentence to be understood;
    • producing, based upon the probability distributions, the meaning of the second sentence, wherein the probability distribution assumes that the sentence E is generated under predetermined semantic rules in non-overlapping substrings such that each substring of the sentence E is generated by one concept in a semantic library, and wherein a set of substrings is called a clumping.


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 - 35pp US4829423  1989-05 Tennant et al.  Texas Instruments Incorporated Menu-based natural language understanding system
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 - 143pp US4914590  1990-04 Loatman et al.  Emhart Industries, Inc. Natural language understanding system
Get PDF - 13pp US5029085  1991-07 Ito  Ricoh Company, Ltd. Conversational-type natural language analysis apparatus
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 - 15pp US5293584  1994-03 Brown et al.  International Business Machines Corporation Speech recognition system for natural language translation
Get PDF - 36pp US5369574  1994-11 Masegi et al.  Canon Kabushiki Kaisha Sentence generating system
Get PDF - 22pp US5680511  1997-10 Baker et al.  Dragon Systems, Inc. Systems and methods for word recognition
       
Foreign References: None

Other Abstract Info: DERABS G2000-012896 DERABS G2000-012896

Other References:
  • C. Y. Suen, "n-Gram Statistics for Natural Language Understand and Text Processing", IEEE Trans. on Pattern Analysis and Machine Intelligence, v.PAMI-1 #2 Apr. 1979, pp. 164-172. (9 pages) Cited by 2 patents
  • R. Kuhn & R.De Mori, "The Application of Semantic Classification Trees to Natural Language Understanding", IEEE Trans. on Pattern Analysis and Machine Intelligence, v.17 #5 May 1995, pp. 449-460. (12 pages) Cited by 7 patents [ISI abstract]
  • R. Pieraccini et al "A Speech Understanding System Based on Statistical Representation of Semantics", IEEE Conf. Proc. of IEEE-ICASSP VI-193-196, Mar. 1992.
  • S. Miller et al., "Hidden Understanding Models of Natural Language", Proc. of 32nd Annual Mtg. of ACL, Jun. 1994, pp. 25-32, Morgan Kaufmann Publishers, Inc.
  • R. Pieraccini et al, "Stochastic Representation of Sematic Structure For Speech Understanding" Eurospeech Communication Assn., v.2, Sept. 1991, 383-386.


  • 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