Abstract | ||
---|---|---|
This paper presents a learning system for identifying syntactic structures. This system relies on the use of background knowledge and default values in order to build up an initial grammar and the use of theory refinement in order to improve this grammar. This combination provides a good machine learning framework for Natural Language Learning. We illustrate this point with the presentation of ALLiS, a learning system which generates a regular expression grammar of non-recursive phrases from bracketed corpora. |
Year | DOI | Venue |
---|---|---|
2000 | 10.3115/990820.990854 | COLING |
Keywords | Field | DocType |
good machine,theory refinement,non-recursive phrase,bracketed corpus,default value,syntactic structure,regular expression grammar,initial grammar,natural language learning,machine learning,regular expression,natural language | Algorithmic learning theory,Active learning (machine learning),Regular tree grammar,Computer science,Grammar,Emergent grammar,Natural language processing,Artificial intelligence,Regular grammar,Stochastic grammar,Mildly context-sensitive grammar formalism | Conference |
Volume | ISBN | Citations |
C00-1 | 1-55860-717-X | 2 |
PageRank | References | Authors |
2.98 | 12 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hervé Déjean | 1 | 377 | 48.52 |