Memory-Based Shallow Parsing

1999/06/02 by Walter Daelemans, Daelemans, Walter, Sabine Buchholz +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.6.2 #I.7.1 #Machine Learning (cs.LG) #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.cs/9906005

8 pages, to appear in: Proceedings of the EACL'99 workshop on Computational Natural Language Learning (CoNLL-99), Bergen, Norway, June 1999

arxiv created 1999/06/02 · arxiv updated 2009/11/30

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.

Related

• Memory-Based Shallow Parsing
• A Learning Approach to Shallow Parsing
• Memory-Based Learning: Using Similarity for Smoothing
• A Memory-Based Approach to Learning Shallow Natural Language Patterns
• Bagging and Boosting a Treebank Parser