Abstract
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Ninth Conference on Natural Language Learning, CONLL-2005, June 29-30 |
| Editors | I. Dagan, D. Gildea |
| Place of Publication | Ann Arbor, MI |
| Publisher | ACL |
| Pages | 80-87 |
| Number of pages | 8 |
| Publication status | Published - 2005 |
Fingerprint
Cite this
}
Improving sequence segmentation learning by predicting trigrams. / van den Bosch, A.; Daelemans, W.
Proceedings of the Ninth Conference on Natural Language Learning, CONLL-2005, June 29-30. ed. / I. Dagan; D. Gildea. Ann Arbor, MI : ACL, 2005. p. 80-87.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
TY - GEN
T1 - Improving sequence segmentation learning by predicting trigrams
AU - van den Bosch, A.
AU - Daelemans, W.
N1 - Pagination: 8
PY - 2005
Y1 - 2005
N2 - Symbolic machine-learning classifiers are known to suffer from near-sightedness when performing sequence segmentation (chunking) tasks in natural language processing: without special architectural additions they are oblivious of the decisions they made earlier when making new ones. We introduce a new pointwise-prediction single-classifier method that predicts trigrams of class labels on the basis of windowed input sequences, and uses a simple voting mechanism to decide on the labels in the final output sequence. We apply the method to maximum-entropy, sparse winnow, and memory-based classifiers using three different sentence-level chunking tasks, and show that the method is able to boost generalization performance in most experiments, attaining error reductions of up to 51%. We compare and combine the method with two known alternative methods to combat near-sightedness, viz. a feedback-loop method and a stacking method, using the memory-based classifier. The combination with a feedback loop suffers from the label bias problem, while the combination with a stacking method produces the best overall results.
AB - Symbolic machine-learning classifiers are known to suffer from near-sightedness when performing sequence segmentation (chunking) tasks in natural language processing: without special architectural additions they are oblivious of the decisions they made earlier when making new ones. We introduce a new pointwise-prediction single-classifier method that predicts trigrams of class labels on the basis of windowed input sequences, and uses a simple voting mechanism to decide on the labels in the final output sequence. We apply the method to maximum-entropy, sparse winnow, and memory-based classifiers using three different sentence-level chunking tasks, and show that the method is able to boost generalization performance in most experiments, attaining error reductions of up to 51%. We compare and combine the method with two known alternative methods to combat near-sightedness, viz. a feedback-loop method and a stacking method, using the memory-based classifier. The combination with a feedback loop suffers from the label bias problem, while the combination with a stacking method produces the best overall results.
M3 - Conference contribution
SP - 80
EP - 87
BT - Proceedings of the Ninth Conference on Natural Language Learning, CONLL-2005, June 29-30
A2 - Dagan, I.
A2 - Gildea, D.
PB - ACL
CY - Ann Arbor, MI
ER -