Memory-Based Shallow Parsing

TL;DR

This paper introduces a memory-based learning approach to shallow parsing tasks like POS tagging, chunking, and syntactic relation identification, achieving competitive results on standard benchmarks.

Contribution

The paper presents a novel memory-based learning framework for shallow parsing, integrating multiple tasks into a unified approach with strong empirical performance.

Findings

93.8% F-value for NP chunking on WSJ

94.7% F-value for VP chunking on WSJ

77.1% F-value for subject detection

Abstract

We present a memory-based learning (MBL) approach to shallow parsing in which POS tagging, chunking, and identification of syntactic relations are formulated as memory-based modules. The experiments reported in this paper show competitive results, the F-value for the Wall Street Journal (WSJ) treebank is: 93.8% for NP chunking, 94.7% for VP chunking, 77.1% for subject detection and 79.0% for object detection.