Part-of-Speech Tagging with Minimal Lexicalization

Details Part-of-Speech Tagging with Minimal Lexicalization Part-of-Speech Tagging with Minimal Lexicalization

2003-12-27

arxiv.org/abs/cs/0312060v1

Computer Science

Computation and Language

10 pages text; 1 figure. To appear in "Current Issues in Linguistic Theory: Recent Advances in Natural Language Processing";Jo

Scientific paper

We use a Dynamic Bayesian Network to represent compactly a variety of sublexical and contextual features relevant to Part-of-Speech (PoS) tagging. The outcome is a flexible tagger (LegoTag) with state-of-the-art performance (3.6% error on a benchmark corpus). We explore the effect of eliminating redundancy and radically reducing the size of feature vocabularies. We find that a small but linguistically motivated set of suffixes results in improved cross-corpora generalization. We also show that a minimal lexicon limited to function words is sufficient to ensure reasonable performance.

Affiliated with

Also associated with

No associations

Rating

Part-of-Speech Tagging with Minimal Lexicalization 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 Part-of-Speech Tagging with Minimal Lexicalization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Part-of-Speech Tagging with Minimal Lexicalization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-513834