| Jiang jifa | ||
| Software
Department Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing, China, 100080 |
(010)
62587953 (O) (010) 96589-371900 (bp) email: jjf@software.ict.ac.cn http://10.3.0.249/jjf/ |
I am now a Ph.D. student in the Software Department, Institute of Computing Technology, Chinese Academy of Sciences, from 1999-2002, working in Knowledge Discovery Group and Machine Translation Group. My doctoral supervisor is Dr. Bai Shuo.
| Research direction: information extraction |
信息抽取的定义：从某个特定的信息源集中抽取符合某个抽取模式的信息项并将之放到结构化数据库的过程。
信息抽取的目的：从技术上为进一步的精确信息检索、统计和数据挖掘等做好了准备。
信息抽取的产生背景：The appearance and development of the Internet/WWW stimulate the dramatic increase of the text-style documents which are connected by the Internet/WWW and can be got easily, quickly and freely wherever and whenever you are. Then the problem is how to find your needed information from this huge information network. IR technology and search engines such as GOOGLE can help people find some related documents quickly, even the precision is not so good. Further more, people want to find some detail information for a special purpose in order to support them to make a decision. For example, monitoring the stock markerts's dynamic changing situation, collecting and monitoring the competition corporation's various information from their websites, collecting various products's prices information used for the comparision of them during the e-trading process, etc. All these things need the support of the information extraction technology.
Other interests: natural language processing, machine learning, statistic analysis and some applications based on these technologies such as machine translation, information retrieval, information filtering, text automatic categorization/clustering, data mining etc.
| 近期工作 |
| 我的文章 |
| Some IE related websites |
| 知识学习、收集语料 |
| 常用搜索引擎 |
| 友情连接 |
| 信息平台 |
| 杂志、刊物 |