Chunk Tagger - Statistical Recognition of Noun Phrases

TL;DR

This paper presents a stochastic partial parsing method using Markov Models that recognizes the internal structure and categories of various syntactic phrases, improving upon traditional bracketing techniques.

Contribution

It introduces a novel Markov Model-based approach for partial parsing that captures internal phrase structure and categories, extending beyond simple boundary detection.

Findings

Achieved high tagging accuracy across different applications

Effectively recognized internal structure of complex phrases

Demonstrated advantages over traditional bracketing methods

Abstract

We describe a stochastic approach to partial parsing, i.e., the recognition of syntactic structures of limited depth. The technique utilises Markov Models, but goes beyond usual bracketing approaches, since it is capable of recognising not only the boundaries, but also the internal structure and syntactic category of simple as well as complex NP's, PP's, AP's and adverbials. We compare tagging accuracy for different applications and encoding schemes.