The Clinical Language Understanding group at Nuance Communications has developed a medical information extraction system that combines a rule-based extraction engine with machine learning algorithms to identify and categorize references to patient smoking in clinical reports. The extraction engine identifies smoking references; documents that contain no smoking references are classified as UNKNOWN. For the remaining documents, the extraction engine uses linguistic analysis to associate features such as status and time to smoking mentions. Machine learning is used to classify the documents based on these features. This approach shows overall accuracy in the 90s on all data sets used. Classification using engine-generated and word-based features outperforms classification using only word-based features for all data sets, although the difference gets smaller as the data set size increases. These techniques could be applied to identify other risk factors, such as drug and alcohol use, or a family history of a disease.

A system is described which digests large volumes of text, filtering out irrelevant articles and distilling the remainder into templates that represent information from the articles in simple slot/filler pairs. The system is highly modular in that it consists of a series of programs, each of which contributes information to the text to help in the final analysis of determining which strings constitute valid values for the slots in the template. This modular design has the dual advantage of allowing relatively easy debugging and of permitting many of the component programs to participate in other projects. The system is customized to specific domains, taking advantage of simple string matching techniques to improve the effectiveness of more complex sentence-level semantic processes. The extension to new domains has been facilitated by dividing system data files into generic vs. specific categories; domain extension requires the creation of only the domain-specific files. © 1993 John Wiley & Sons, Inc.

In this study we map out a way to build event representations incrementally, using information which may be widely distributed across a discourse. An enhanced Discourse Representation (Kamp, 1981) provides the vehicle both for carrying open event roles through the discourse until they can be instantiated by NPs, and for resolving the reference of these otherwise problematic NPs by binding them to the event roles.