Publication: Co-occurrence-based error correction approach to word segmentation
Issued Date
2011-09-09
Resource Type
Other identifier(s)
2-s2.0-80052394809
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Proceedings of the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24. (2011), 240-244
Suggested Citation
Ekawat Chaowicharat, Kanlaya Naruedomkul Co-occurrence-based error correction approach to word segmentation. Proceedings of the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24. (2011), 240-244. Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/11773
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Co-occurrence-based error correction approach to word segmentation
Author(s)
Other Contributor(s)
Abstract
To overcome the problems in Thai word segmentation, a number of word segmentation has been proposed during the long period of time until today. We propose a novel Thai word segmentation approach so called Co-occurrence-Based Error Correction (CBEC). CBEC generates all possible segmentation candidates using the classical maximal matching algorithm and then selects the most accurate segmentation based on co-occurrence and an error correction algorithm. CBEC was trained and evaluated on BEST 2009 corpus. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.