An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars

Simple item page
dc.creatorHwa, Rebecca
dc.date1998-08-04
dc.date.accessioned2026-07-07T02:36:19Z
dc.date.available2026-07-07T02:36:19Z
dc.descriptionWe present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (PCFG), to problems in stochastic natural-language processing. Comparing the performance of PLTIGs with non-hierarchical N-gram models and PCFGs, we show that PLTIG combines the best aspects of both, with language modeling capability comparable to N-grams, and improved parsing performance over its non-lexicalized counterpart. Furthermore, training of PLTIGs displays faster convergence than PCFGs.
dc.description10 pages, 6 encapsulated postscript figures and 2 latex figures, uses colacl.sty
dc.identifierhttps://arxiv.org/abs/cmp-lg/9808001
dc.identifierhttp://arxiv.org/abs/cmp-lg/9808001
dc.identifierProceedings of COLING-ACL'98
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/15877
dc.subjectComputation and Language
dc.titleAn Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars
dc.typetext

Files

Collections

arXiv