[54] PARSING METHOD AND SYSTEM FOR NATURAL LANGUAGE PROCESSING
[75] Inventor: Tetsuya Nasukawa, Hachioji, Japan
[73] Assignee: International Business Machines Corporation, Armonk, N.Y.
[21] Appl. No.: 501,749
[22] Filed: Jul. 12, 1995
[30] Foreign Application Priority Data
Nov. 17, 1994 [JP] Japan 6-283087
[51] Int CL6 G06F 17/27
[52] U.S.C1 704/9
[58] Field of Search 395/751. 752.
395/754, 755. 759. 760; 704/1. 2, 4. 5,
9. 10
[56] References Cited
U.S. PATENT DOCUMENTS
5,128,865 7/1992 Sadler.
5,136,503 8/1992 Takagi et al. .
5,225,981 7/1993 Yokogawa.
5,297,039 3/1994 Kanaegami et al. .
5,311,429 5/1994 Tominaga.
5,396,419 3/1995 Morimoto .
5,424,947 6/1995 Nagao et al. .
5,495,413 2/1996 Kutsumi et al. .
Primary Examiner—Robert A. Weinhardt
[57] ABSTRACT
The present invention provides a method and system to improve the accuracy of natural language processing systems by enabling them to acquire a parsing output that is accurate to a degree for any type of sentence. The feature of the present invention is that a sentence (a non-grammatical, ill-formed sentence) that cannot be parsed when using a conventional parsing process, which relies on grammatical knowledge, is re-analyzed by using the parsing results for an identical word row in a sentence (a well-formed sentence) in the same context that could be parsed. More specifically, the processing below is performed: (1) a well-formed sentence in a context that includes a word row that is identical to a word row in an ill-formed sentence is searched for. and a dependency structure for that word row is extracted from the parsing results for the well-formed sentence; and (2) the dependency structures of the phrases obtained in (1) are linked by referring to linking information for the wellformed sentence and a grammar, and the dependency structure of the entire sentence is introduced.
22 Claims, 20 Drawing Sheets
