An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars

Details An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars

1998-08-04

arxiv.org/abs/cmp-lg/9808001v1

Proceedings of COLING-ACL'98

Computer Science

Computation and Language

10 pages, 6 encapsulated postscript figures and 2 latex figures, uses colacl.sty

Scientific paper

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 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.

Affiliated with

Also associated with

No associations

Rating

An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-393816