Experimental Study of Chinese Free-Text IE Algorithm Based on W_(CA)-Selection Using Hidden Markov Model

摘要

This paper proposes the extraction task of the Chinese Sci-tech journal text and presents a W_(CA)-Selection Chinese free-text HMM IE algorithm. The HMM IE algorithm takes the Chinese Sci-tech journal abstract text as the extraction text. According to the features of W_(CA), an idea of W_(CA) selection model re-optimization is proposed. And a W_(CA) selection optimization strategy is concreted. Then the experimental verification is conducted with a satisfied result. The experiment results show that the designed extraction algorithm and W_(CA) selection optimization strategy have good performance in the the Chinese Sci-tech journal abstract text.