A gradual refinement model for a robust thai morphological analyzer

Authors:
Kawtrakul Asanee;Thumkanon Chalatip;Jamjanya Thitima;Muangyunnan Parinee;Poolwan Kritsada;Inagaki Yasuyoshi
Affiliations:
Kasetsart University, Bangkok, Thailand;Kasetsart University, Bangkok, Thailand;Kasetsart University, Bangkok, Thailand;Kasetsart University, Bangkok, Thailand;Kasetsart University, Bangkok, Thailand;Nagoya University, Chikusa-ku, Nagoya, Japan
Venue:
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2
Year:
1996

Citing 6
Cited 0

Statistical Language Learning

Statistical Language Learning
Probabilistic tagging with feature structures

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
An evaluation to detect and correct erroneous characters wrongly substituted, deleted and inserted in Japanese and English sentences using Markov models

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
A stochastic Japanese morphological analyzer using a forward-DP backward-A* N-best search algorithm

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Syllable-based model for the Korean morphology

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Segmenting a sentence into morphemes using statistic information between words

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1

Quantified Score

Hi-index	0.01

Visualization

Abstract

This work attempts to provide a robust Thai morphological analyzer which can automatically assign the correct part-of-speech tag to the correct word with time and space efficiency. Instead of using a corpus based approach with requires a large amount of training data and validation data, a new simple hybrid technique which incorporates heuristic, syntactic and semantic knowledge is proposed. To implement this technique, a three-stage approach is adopted to the gradual refinement module. It consists of preference based pruning, syntactic based pruning and semantic based pruning, Each stage will gradually weeds out word boundary ambiguities, tag ambiguities and implicit spelling errors. From the result of the experiment, the proposed model can work with time-efficiency and increase the accuracy of word boundary segmentations, POS tagging as well as implicit spelling error correction.