Deep textual semantics acquisition based on the activation of domain knowledge

The acquisition of deep textual semantics is a key issue on the process of text understanding which improves the performances of e-learning, web search and web services significantly. Though many methods have been developed to acquire textual semantics, the acquisition of deep textual semantics is still a challenge issue. Herein, the acquisition method of deep textual semantics is developed to enhance the capability of text understanding of machine, including two parts:1) how to obtain and organize the domain knowledge extracted from domain text set; 2) how to stimulate the domain knowledge for obtaining the deep textual semantics. The activation process involves two cognitive mechanisms; one is the Landscape model and the other is human memory system model. The former model is a human reading model. The later model describes the memory change in the text reading process. Generalized semantic field is proposed to store the domain knowledge as the form of Long Time Memory (LTM). Specialized semantic field, which is acquired by the interaction between the text fragment and the domain knowledge, is introduced to describe the change process of textual semantics. By their mutual actions, we can get the deep textual semantics which enhances the capability of text understanding of machine; therefore, the machine can understand the text more precisely and correctly than those methods which only obtain surface textual semantics.