Information Extraction System Based on Hidden Markov Model

摘要

A novel approach using Hidden Markov Model (HMM) for the task of finding prices of products on internet sites is proposed in this paper. The proposed Information Extraction System based on HMM (IESHMM) utilizes HMM for its capability to process temporal information. The proposed IESHMM first processes web pages that are returned from search engines and then extracts specific fields such as prices, descriptions, locations, images of products, and other information of interest. The proposed IESHMM is evaluated with real-world problems and compared with a conventional method. The results show that the proposed IESHMM outperforms the other method by 22.9 % and 37.2% in terms of average recall and average precision, respectively.