【正文】
nt of a prototype of universal Information Extraction system is described. The main features of this system are: 1) using shallow parsing technology with sentence semantic template to extract the information in the text。在本論文研究工作中,作者所在的研究小組試圖建立一種信息系統(tǒng)的開(kāi)發(fā)原型,其特點(diǎn)在于利用淺層語(yǔ)法語(yǔ)義分析系統(tǒng)配合句法模版提取信息,并充分利用現(xiàn)代計(jì)算機(jī)系統(tǒng)并行處理的優(yōu)勢(shì),使用多線程的編程技巧充分利用計(jì)算機(jī)的處理能力加 速信息提取系統(tǒng)的運(yùn)行速度。 Yahoo的系統(tǒng)開(kāi)發(fā)與商業(yè)運(yùn)作經(jīng)驗(yàn)充分證明了商業(yè)化運(yùn)作是技術(shù)開(kāi)發(fā)可以 ?獲得成功的關(guān)鍵因素。信息提取系統(tǒng)的運(yùn)行需要 Inter的支持。國(guó)外因?yàn)槿肆Y源價(jià)值高昂的緣故,應(yīng)用尤其廣泛,甚至為了加快信息系統(tǒng)的數(shù)據(jù)錄入工作而在數(shù)據(jù)庫(kù)的信息錄入模塊中嵌入簡(jiǎn)化的使用自然語(yǔ)言分析技術(shù)的信息提取模塊。 4) Chinese language is its working language. Secondly, the research of how the IE system to improve the enterprise information utilizing are also discussed. Today, many large Chinese enterprises use MIS, MRPII or ERP system to improve their business management. The knowledge management technology is a very important aid to help the development of the enterprise. IE system can bee the main part of the knowledge management system. Last part of this thesis is about how to build a proper business model for a