How can you begin to search the mountains of data that exist in a multitude of formats on all of your digital storage, and come up with useful structured data? Information Extraction bridges the gap between piles of unstructured documents and the database.
Information extraction is enabled by a number of technologies, one of which is "Named Entity Recognition". The effect of all information extraction is to extract pre-categorized structured text data from any type of unstructured data source, helping you put your data to work. Have you ever struggled to find an important address buried in a long-forgotten email? Intuidex's information extraction can take your disorganized email archive and give you a complete address book!
Intuidex's IxEE™ platform is a mature combination of effective information extraction technologies, the result of man-years of effort by information engineers and domain experts. IxEE™ is a core component in all of Intuidex's advanced data analytics products.
Read about IxEEE™, Intuidex's powerful entity extraction engine.
Related links from Dr. Pottenger's Research:
Wu, T. and Pottenger, W. M. (2005) A Semi-Supervised Active Learning Algorithm for Information Extraction from Textual Data. Journal of the American Society for Information Science and Technology, JASIST, Volume 56, Number 3, Pages 258-271.
Li, S., Janneck, C., Belapurkar, A., Ganiz, M. C., Yang, X., Dilsizian, M. D., Wu, T., Bright, J. and Pottenger, W. M. (2007) Mining Higher-Order Association Rules from Distributed Named Entity Databases. In the Proceedings of the IEEE International Conference on Intelligence and Security Informatics 2007 (ISI 2007), New Brunswick, NJ, May.
Links to other information on Information Extraction