Abstract | ||
---|---|---|
We address the issue of how to associate frequency information with lexicalized grammar formalisms, using Lexicalized Tree Adjoining Grammar as a representative framework. We consider systematically a number of alternative probabilistic frameworks, evaluating their adequacy from both a theoretical and empirical perspective using data from existing large treebanks. We also propose three orthogonal approaches for backing off probability estimates to cope with the large number of parameters involved. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1007/978-94-015-9470-7_2 | Clinical Orthopaedics and Related Research |
Keywords | Field | DocType |
lexicalized grammars,probabilistic parsing | Tree-adjoining grammar,Rule-based machine translation,Programming language,Computer science,Grammar,Artificial intelligence,Natural language processing,Probabilistic logic,Rotation formalisms in three dimensions,Encoding (memory) | Journal |
Volume | ISSN | Citations |
cmp-lg/970 | 5th International Workshop on Parsing Technologies (IWPT-97) | 10 |
PageRank | References | Authors |
1.63 | 21 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
John Carroll | 1 | 1971 | 222.19 |
David J. Weir | 2 | 840 | 83.84 |