DMCA
Single-Classifier Memory-Based Phrase Chunking (2000)
| Venue: | In Proceedings of CoNLL-2000 and LLL-2000 |
| Citations: | 13 - 1 self |
BibTeX
@INPROCEEDINGS{Veenstra00single-classifiermemory-based,
author = {Jorn Veenstra and Antal van den Bosch},
title = {Single-Classifier Memory-Based Phrase Chunking},
booktitle = {In Proceedings of CoNLL-2000 and LLL-2000},
year = {2000},
pages = {157--159}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Introduction In the shared task for CoNLL-2000, words and tags form the basic multi-valued features for predicting a rich phrase segmentation code. While the tag features, containing WSJ part-ofspeech tags (Marcus et al., 1993), have about 45 values, the word features have more than 10,000 values. In our study we have looked at how memory-based learning, as implemented in the TiMBL software system (Daelemans et al., 2000), can handle such features. We have limited our search to single classifiers, thereby explicitly ignoring the possibility to build a metalearning classifier architecture that could be expected to improve accuracy. Given this restriction we have explored the following: 1. The generalization accuracy of TiMBL with default settings (multi-valued features, overlap metric, feature weighting). 2. The usage of MVDM (Stanfill and Waltz, 1986; Cost and Salzberg, 1993) (Section 2), which should work well on word value pairs with a medium or high frequency, but may wor
Keyphrases
single-classifier memory-based phrase chunking generalization accuracy default setting metalearning classifier architecture word value wsj part-ofspeech tag tag feature rich phrase segmentation code high frequency basic multi-valued feature single classifier multi-valued feature memory-based learning timbl software system
