Sciweavers

ACL
1998

An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars

13 years 5 months ago
An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars
We 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 naturallanguage 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 nonlexicalized counterpart. Furthermore, training of PLTIGs displays faster convergence than PCFGs.
Rebecca Hwa
Added 01 Nov 2010
Updated 01 Nov 2010
Type Conference
Year 1998
Where ACL
Authors Rebecca Hwa
Comments (0)