Search

Semantic knowledge-base has important meaning for increasing the deepness of NLP. Some comparatively mature Semantic knowledge-base such as WordNet, HowNet and Thesaurus was developed by manpower, and has many difficulties on actual application. In order to capture Chinese word knowledge of relating status moue automatically and demonstrably, this paper presented the concept of word correlation and a calculation method of word correlation based on statistic. Then a correlation net based on Chinese words which have strong domain characteristic was built. In order to resolve the difficulty of processing the huge amount of data, a hard disk storing method of array segmentation was designed. The semantic knowledge gained by the experiment had the advantage of empiricism. It is veracity and generalization is strong so it can play an important role in many fields such as text categorization, text retrieval, text filtering, etc.

Cognitive attacks, which influence the user’s perceptions and behavior, are more serious than physical or even syntactic attacks. We construct an attack model for cognitive Network based on scientific analysis of Network material system to visualize cognitive attack. The cognitive attack model consists of two parts: attackers and netizens. We formalize each element of the model. The cognitive attack example analysis illustrates the rationality of the model.

The present Extraction for Keyword in Chinese (EKC for short) is merely directed against explicit keywords or prototype keywords, and has not take into account those tacit keywords distorted by network hackers with the method of active jamming in Chinese. For this purpose, with the help of M. Polanyi’s theory of tacit knowledge, this paper presents a new approach for the tacit EKC (TEKC for short), which can improve the ratio of precision and recall for information filtering. Based on the TEKC, the paper presents a set of classifications of how to distort the explicit keywords and the solutions to calculate the tacit distortion of those tacit keywords. Furthermore, 4 algorithms were designed, including in picture tacit, textspeak tacit, fake paleography tacit and character tacit, which can extract the tacit keywords in text but traditional EKC could not. Owing to the increased number of extracted keywords, the recall of keywords raised and the precision of information filtering improved. Experiments show that the classification of tacit keywords in Chinese, the calculation of tacit distortion and the algorithms to tacit extract the keywords in Chinese, etc can effectively improve the performance of EKC and raise the recall of web filtering algorithms based on TEKC.

Biologically-inspired methods such as evolutionary algorithms and neural networks are well suited to dynamic problems. Artificial immune systems are proving useful in the field of information filtering. We tackle this dynamic problem with IHIF, a harmful information filtering model inspired by the immune system. It is based on a self-organising antibody network that reacts to dynamic evolvement in order to define and preserve the features of harmful Web pages. The experiment results demonstrate IHIF’s ability to filter harmful information.