A New Approach to Online Generation of Association Rules
IEEE Transactions on Knowledge and Data Engineering
Discovery of Multiple-Level Association Rules from Large Databases
VLDB '95 Proceedings of the 21th International Conference on Very Large Data Bases
Data Mining: Concepts and Techniques
Data Mining: Concepts and Techniques
Hi-index | 0.00 |
The semantic collocations play important roles in parsing Chinese phrases. They are useful for both semantic disambiguation and structural disambiguation. In this paper, a representation of phrase semantic rules for Chinese is presented to formulate such knowledge, and a corpus-based method was proposed to acquire phrase semantic rules from a Chinese phrase corpus annotated with syntactic and semantic information. The method includes a metarule-guided algorithm for mining cross-level association rules to acquire phrase semantic rules and an optimization algorithm to filter these rules. The experiment results showed the effectiveness of the method. Disambiguation performance of these resulting rules was quiet well.