Memory-Based Shallow Parsing

Add code
Jun 02, 1999
Walter Daelemans, Sabine Buchholz, Jorn Veenstra
Figure 1 for Memory-Based Shallow Parsing
Figure 2 for Memory-Based Shallow Parsing
Figure 3 for Memory-Based Shallow Parsing
Figure 4 for Memory-Based Shallow Parsing

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

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

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon