An evaluation of text analysis technologies
AI Magazine
Communications of the ACM
An empirical study of automated dictionary construction for information extraction in three domains
Artificial Intelligence - Special volume on empirical methods
Issues in inductive learning of domain-specific text extraction rules
Connectionist, Statistical, and Symbolic Approaches to Learning for Natural Language Processing
CRYSTAL inducing a conceptual dictionary
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
A word-based approach for modeling and discovering temporal relations embedded in Chinese sentences
ACM Transactions on Asian Language Information Processing (TALIP)
Mining free text for structure
Data mining
A model for processing temporal references in Chinese
TASIP '01 Proceedings of the workshop on Temporal and spatial information processing - Volume 13
| Hi-index | 0.00 |
MetLife processes over 300,000 life insurance applications a year. Undernriting of these applications is labor intensive. Automation is difficult since they include many free-form text fields. MITA, MetLife's Intelligent Text Analyzer, uses the Infonnation Extraction --IE-- technique of Natural Language Processing to structure the extensive text fields on a life insurance application. Knowledge engineering, with the help of underwriters as domain experts, was performed to elicit significant concepts for both medical and occupational text fields. A corpus of 20,000 life insurance applications provided the syntactical and semantic patterns in which these underwriting concepts occur. The extracted information can then be analyzed by conventional knowledge based systems. We project that MITA and knowledge based analyzers will increase underwriting productivity by 20 to 30%.