E-Science environment-oriented multi-domain Web text feature extracting system and method

Abstract

The invention relates to an e-Science environment-oriented multi-domain Web text feature extracting system and method. The method comprises the following steps of: 1. making statistics on the frequentness of characters in a target text; 2. with a character as a basic processing unit, extracting character strings between the character used as a start point and a character having the frequentness of 1 and being used as a terminal point one by one; and 3. making statistics of the frequentness of each character string, and performing descending order on feature character strings according to the frequentness and outputting the feature character strings. In the invention, a non-dictionary character segmentation technology is introduced in the feature discovery of a domain text, thereby the dependence of a traditional method on a domain dictionary is effectively overcome and the portability and the practicability of the e-Science environment-oriented multi-domain Web text feature extracting system and method in multi-domain scientific data are enhanced to some extent.

Description

technical field [0001] The invention relates to feature extraction of Web text, in particular to a multi-field Web text feature extraction system and method for e-Science environment. Background technique [0002] Khaled Khelif (2007) proposed an ontology-based information extraction method, aiming to help biologists acquire professional knowledge more effectively. This method relies on semantic annotation of scientific and technological documents, automatically generates domain ontology and provides corresponding information retrieval interface. Tara McIntosh (2007) proposed a full-text information extraction system for the biomedical field to solve the shortcomings of the traditional analysis methods based on literature summarization. Ziya Ozkan Gokturk and Nihan Kesim Cicekli et al. (2007) used web crawler technology to extract and classify web page metadata using pre-set regular expressions. In the experiment, taking the European Cup and the UEFA Champions League as ex...

AI Technical Summary

Problems solved by technology

[0003] Existing domain-based information extraction methods mostly rely on domain dictionaries to discover text features, which is neither convenient for experimental reproduction, nor easy for transplantation and promotion in multi-domain environments, which seriously restricts the application range of Chinese information extraction systems

In the analysis process, it mostly relies on the assistance of domain dictionaries or tagged word sets. Although it can effectively improve the extraction accuracy of specific domain features, it cannot meet the actual needs of multi-domain information extraction in terms of system portability.

Images