DMCA
Word sense disambiguation using label propagation based semi-supervised learning (2005)
Cached
Download Links
| Venue: | Proceedings of the ACL |
| Citations: | 29 - 4 self |
BibTeX
@INPROCEEDINGS{Niu05wordsense,
author = {Zheng-yu Niu and Dong-hong Ji},
title = {Word sense disambiguation using label propagation based semi-supervised learning},
booktitle = {Proceedings of the ACL},
year = {2005},
publisher = {ACL}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Shortage of manually sense-tagged data is an obstacle to supervised word sense disambiguation (WSD) methods. In this paper we investigate a label propagation based semi-supervised learning algorithm for WSD, which combines unlabeled data with labeled data in learning process by representing labeled and unlabeled examples as vertices in a weighted graph and iteratively propagating the label information from any vertex to nearby vertices until this process converges. This label propagation process realizes a global consistency assumption: similar examples should have similar labels. Our experimental results on benchmark corpora indicate that it consistently outperforms SVM when only very few labeled examples are available, and its performance is also better than monolingual bootstrapping, and comparable to bilingual bootstrapping. 1
Keyphrases
label propagation word sense disambiguation semi-supervised learning unlabeled example bilingual bootstrapping benchmark corpus unlabeled data label information sense-tagged data semi-supervised learning algorithm global consistency assumption similar label similar example monolingual bootstrapping nearby vertex experimental result label propagation process weighted graph
