■H IF11II Oil 111 I PI
United States Patent  [ii] Patent Number: 5,642,522
Zaenen et al.  Date of Patent: Jun. 24, 1997
 CONTEXT-SENSITIVE METHOD OF
FINDING INFORMATION ABOUT A WORD
IN AN ELECTRONIC DICTIONARY
 Inventors: Annie E. Zaenen; Lauri J. Karttunen,
both of Redwood City, Calif.
 Assignee: Xerox Corporation, Stamford, Conn.
 Appl. No.: 396,286
 Filed: Feb. 28,1995
Related U.S. Application Data
 Continuation of Set No. 100,960, Aug. 3,1993, abandoned.
 Int CI.6 G06F 17/27
 U.S. CI 395/794; 395/759
 Field of Search 364/419.04, 419.05,
364/419.08, 419.1, 419.11; 395/754, 755, 759, 792, 793, 794
 References Cited
U.S. PATENT DOCUMENTS
4,661,924 4/1987 Okamoto et al. .
4,864,501 9/1989 Kucera et al. .
4,868,750 9/1989 Kucera et al. .
4,942,526 7/1990 Okajima et al. .
4,984,178 1/1991 Hemphill et al. .
5,099,425 3/1992 Kanno et al. .
5,146,405 9/1992 Church.
5,243,520 9/1993 Jacobs et al. .
5,289,376 2/1994 Yokogawa.
5,295,070 3/1994 Justice.
FOREIGN PATENT DOCUMENTS
0 525 470 A2 2/1993 European Pat. Off. .
JJ. Hull, "A Hidden Markov Model for Language Syntax in
Text Recognition" 11th IAPR International Conference on
Pattern Recognition (Aug. 30, 1992-Sep. 3, 1992) The
Hague, Netherlands Abstract No. 4297590.
Lauri Karttunen. Finite-State Constraints. International
Conf. on Current Issues in Computational Linguistics. Jun.
24, 1991. pp. 1-18.
Lauri Karttunen, et al. Two-Level Morphology with Composition. Proceedings of Coling -92. Published Jul. 25-28, 1992. 10 pgs.
Lawrence R. Rabiner. ATutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the JEEE, vol. 77, No. 2, Feb. 1989. pp. 257-285. Julian Kupiec. Robust part-of-speech tagging using a hidden Markov model. Computer Speech and Language. 1992. vol. 6. pp. 225-242.
Primary Examiner—-Robert A. Weinhardt
Attorney, Agent, or Firm—^Townsend and Townsend and
A technique of using an electronic dictionary in conjunction with electronically-encoded running text that gives the user the most relevant information rather than belaboring the user with all possible information about a selected word. The technique maps the selected word from its inflected form to its citation form, analyzes the selected word in the context of neighboring and surrounding words to resolve ambiguities, and displays the information that is determined to be the most likely to be relevant The dictionary preferably has information about multi-word combinations that include the selected word, and the context determination typically entails checking whether the selected word is part of a predefined multi-word combination.
7 Claims, 3 Drawing Sheets