Data processing: speech signal processing – linguistics – language – Linguistics – Dictionary building – modification – or prioritization
Reexamination Certificate
1998-05-12
2001-02-20
Isen, Forester W. (Department: 2747)
Data processing: speech signal processing, linguistics, language
Linguistics
Dictionary building, modification, or prioritization
Reexamination Certificate
active
06192333
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to computerized language systems. In particular, the present invention relates to dictionaries used in computerized language systems.
Computerized language systems include a wide array of computer implemented functions that manipulate language to improve communication between a computer and a user. Examples include text-to-speech and speech-to-text converters, as well as natural language systems. In each of these systems, the computer must be able to determine the syntax of a sentence. In speech systems the syntax allows the computer to identify the proper tonal inflection for the speech. In natural language systems, the syntax allows the computer to identify the key words in a sentence.
To determine syntax in a sentence, computerized language systems rely on dictionaries that list valid words for a particular language. Preferably, each dictionary entry indicates the word's part of speech and its stem, also known as its lemma. For example, a dictionary entry for “wash” would indicate that the word is a noun and a verb, while the entry for “elate” would indicate that the word is only a verb.
In the art, such dictionaries are built by hand. This requires a great deal of time, which greatly increases the cost of producing computerized language systems for the various languages of the world.
SUMMARY OF THE INVENTION
A computer readable medium has computer executable components that include a morphological analyzer capable of using a corpus of words to automatically form a dictionary containing words associated with a lemma and a part of speech. The computer executable components also include a dictionary analyzer capable of automatically improving the dictionary.
REFERENCES:
patent: 4862408 (1989-08-01), Zamora
patent: 4887212 (1989-12-01), Zamora et al.
patent: 5099426 (1992-03-01), Carlgren et al.
patent: 5229936 (1993-07-01), Decker et al.
patent: 5251316 (1993-10-01), Anick et al.
patent: 5412567 (1995-05-01), Kartunen
patent: 5724594 (1998-03-01), Pentheroudakis
patent: 5794177 (1998-08-01), Carus et al.
patent: 5845306 (1998-12-01), Schabes et al.
patent: 5873660 (1999-03-01), Walsh et al.
patent: 5940624 (1999-08-01), Kadashevich et al.
patent: 5995922 (1999-11-01), Pentheroudakis et al.
patent: 0 282 721 A2 (1988-09-01), None
Sproat,R., “Morphology and Computation.” The MIT Press 1992. pp. 5-7 and 33-34.
Riloff et al., “Automated Dictionary Construction for Information Extraction from Text”,Proceedings of the Ninth Conference on Artificial Intelligence for Applications, Mar. 1-5, 1993, pp. 93-99.
Chen et al., “Automatic Thesaurus Generation for an Electronic Community System”,Journal of the American Society for Information Science, vol. 46, No. 3, 1995, pp. 175-193.
Xu et al., “Corpus-based Stemming Using Coocurrence of Word Variants”,ACM Transactions on Information Systems, vol. 16, No. 1, Jan. 1998, pp. 61-81.
Kuhlen, : Morphological relations by Reduction Algorithms,Database Inspec 'Online! Institute of Electrical Engineers, Stevenage, GB, Inspec No. 700999, Nachrichten Für Dokumentation, vol. 25, No. 4, 1974, pp. 168-172.
Edouard Patrick N.
Isen Forester W.
Microsoft Corporation
Westman Champlin & Kelly P.A.
LandOfFree
System for creating a dictionary does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System for creating a dictionary, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for creating a dictionary will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2601542