Representing Clinical Narratives Using Conceptual Graphs

Abstract

Abstract:The analysis of medical narratives and the generation of natural language expressions are strongly dependent on the existence of an adequate representation language. Such a language has to be expressive enough in order to handle the complexity of human reasoning in the domain. Sowa’s Conceptual Graphs (CG) are an answer, and this paper presents a multilingual implementation, using French, English and German. Current developments demonstrate the feasibility of an approach to natural Language Understanding where semantic aspects are dominant, in contrast, to syntax driven methods. The basic idea is to aggregate blocks of words according to semantic compatibility rules, following a method called Proximity Processing. The CG representation is gradually built, starting from single words in a semantic lexicon, to finally give a complete representation of the sentence under the form of a single CG. The process is dependent on specific rules of the medical domain, and for this reason is largely controlled by the declarative knowledge of the medical Linguistic Knowlege Base.

Natural Language Processing in Medicine: An Overview

“…The obvious advantage of the semantically-driven approach is the robustness of the processor when confronted with agrammaticalities. A semantically-driven parser can more easily take care of agrammatical input thanks to the available knowledge of the domain model [181]. However, it is possible for a syntactically-driven approach (e. g., using a chart parser) to pass partially analyzed sentence chunks to the semantic analyzer that will try to aggregate them correctly.…”

Medical Informatics

“…al., 1987) or conceptual graphs (Baud, Rassinoux, et. tables, domainspecific abbreviations, missing punctuations).…”

Concept-oriented Standardization and Statistics-oriented Classification: Continuing the Classification versus Nomenclature Controversy

“…(2) Especially when we speak about qualitative medical language data, there is a need for standardizing the language data in two senses of the word: (i) Standardizing the data by transforming the meaning into a languageindependent representation based on concept systems that support the processing and exchange of that data. This kind of standardization is concept oriented and carried out by what is called indexing [8,9].…”

“…Especially for indexing, the effort for coding can be shifted to a computerized "coding clerk". This is possible because concept systems provide a conceptual lexicon and grammar suitable for natural language processing approaches [8,9]. However, as outlined earlier, concept systems do not provide explicit questions and instructions for answering them uniquely.…”