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.
Cite
@article{arxiv.cs/9906005,
title = {Memory-Based Shallow Parsing},
author = {Walter Daelemans and Sabine Buchholz and Jorn Veenstra},
journal= {arXiv preprint arXiv:cs/9906005},
year = {2007}
}
Comments
8 pages, to appear in: Proceedings of the EACL'99 workshop on Computational Natural Language Learning (CoNLL-99), Bergen, Norway, June 1999