In view of the current status that in domestic oil field information extraction system Chinese information ex-traction is not accurate ,a more accurate solution of Chinese information extraction based on oilfield is proposed .Under the framework of GATE ,Chinese information extraction plug-in is developed to slove the Chinese segmentation ,Chinese corpus vocabulary and Chinese named entity recognition based on the oil field ,which is applied in business practice .Good results have been achieved ,and the information extraction technology provides research foundation for oil field follow-up research .%针对目前国内油田信息抽取系统中文信息抽取不准确的现状,提出了更为准确的基于油田的中文信息抽取的解决方案。在GA T E框架下,开发中文信息抽取插件,解决了基于油田的中文分词、中文语料词表和中文命名实体识别,并在企业实际中进行了应用,取得了较好的应用效果,并为后续的油田信息抽取技术研究提供了研究基础。
展开▼