Identifying relationships between concepts is a key aspect of scientific knowledge synthesis. Finding these links often requires a researcher to laboriously search through scientific papers and databases, as the size of these resources grows ever larger. In this paper we describe how distributional semantics can be used to unify structured knowledge graphs with unstructured text to predict new ...

Natural language generation in the medical domain is heavily influenced by domain knowledge and genre-specific text characteristics. We present SemScribe, an implemented natural language generation system that produces doctor’s letters, in particular descriptions of cardiological findings. Texts in this domain are characterized by a high density of information and a relatively telegraphic style...

Herein, theory of and practical experiences with the user friendly, Medical Electronic Expert Consultation System (MECES, www.diagnomx.eu) are described. Theoretical considerations: The demands of an adequate communication system that acquires and transfers medical information can be fulfilled by use of open access sources and tools. Development and implementation: MECES uses a common forum fra...

In this paper, we want to describe a tag-ger/lemmatiser for Dutch medical vocabulary , which consists of a full-form dictionary and a morphological recogniser for unknown vocabulary coupled to an expert system-like disambiguation module. Attention is also paid to the main datastructures: a lexical database and feature bundles implemented as directed acyclic graphs. Some evaluation results are p...

In this paper, we introduce our project aiming to build a medical ontology, and also present a method to estimate term relations and term classification, which are the basic structure for the ontology. First, relations between medical terms are extracted from a medical electronic dictionary. Next, the terms are classified based on the co-occurrence verbs. Preliminary experimental results show t...

This paper describes the basic philosophy and implementation of MPLUS (M+), a robust medical text analysis tool that uses a semantic model based on Bayesian Networks (BNs). BNs provide a concise and useful formalism for representing semantic patterns in medical text, and for recognizing and reasoning over those patterns. BNs are noise-tolerant, and facilitate the training of M+.

Blue Cross and Blue Shield of Vermont (BCBSVT) Medical Policies are developed to provide clinical guidance and are based on research of current medical literature and review of common medical practices in the treatment and diagnosis of disease. The applicable group/individual contract and member certificate language determines benefits that are in effect at the time of service. Since medical pr...