Noun Phrase Identification Based on Genetic Algorithm and Hidden Markov Model
To increase further the accuracy of noun phrase(NP) identification and utilize features of genetic algorithm(GA) and the hidden markov model(HMM),a novel method of Np identification is proposed which combines GA and HMM. The method is based on a high-performance POS(parts of speech) tagging. During the training phase, model parameters are gained by genetic algorithm. And during the identifying phase, an improved Viterbi algorithm for dynamic programming is first presented to identify the same hierarchy noun phrase, then the combined method of hierarchical scanning algorithm and Viterbi algorithm is brought forward to identify those recursive noun phrases. Experimental results show that this combined approach has achieved a high precision and recall rate of over 94％, fully inosculating the strength of genetic algorithm and hidden markov model. This proves that the combined method has much better identification effect than the unitary hidden markov model identification approach.
phrase recognition genetic algorithm hidden markov model, viterbi algorithm, hierarchical analysis
LI Rong ZHENG Jiaheng
Computer Department Xinzhou Teachers College Xinzhou, Shanxi Province 034000, China School of Computer and Information Technology Shanxi University Taiyuan, Shanxi Province 030006, Chi
国际会议
武汉
英文
17-20
2007-07-25（万方平台首次上网日期，不代表论文的发表时间）