Applying explanation-based learning to natural-language processing (part 1)
Number of Authors: 1
1989 (English)Report (Refereed)
It is shown how ideas adapted from recent work on explanation-based generalization can be used to allow a logic grammar to "learn" useful derived grammar rules by generalizing them from example sentences. The method is presented in the form of a small Prolog meta-interpreter, and its soundness is formally proved. Examples are given showing the application of the generalizer, first to a toy grammar with 40 rules and then to a largish independantly developed system which involves non-trivial syntactic and semantic analysis.
Place, publisher, year, edition, pages
Kista, Sweden: Swedish Institute of Computer Science , 1989, 1. , 16 p.
SICS Research Report, ISSN 0283-3638 ; R89:14
Computer and Information Science
IdentifiersURN: urn:nbn:se:ri:diva-22176OAI: oai:DiVA.org:ri-22176DiVA: diva2:1041719
Original report number R89014.2016-10-312016-10-31Bibliographically approved