Natural Language Processing and Semantical Representation of Medical Texts

Abstract

Abstract:For medical records, the challenge for the present decade is Natural Language Processing (NLP) of texts, and the construction of an adequate Knowledge Representation. This article describes the components of an NLP system, which is currently being developed in the Geneva Hospital, and within the European Community’s AIM programme. They are: a Natural Language Analyser, a Conceptual Graphs Builder, a Data Base Storage component, a Query Processor, a Natural Language Generator and, in addition, a Translator, a Diagnosis Encoding System and a Literature Indexing System. Taking advantage of a closed domain of knowledge, defined around a medical specialty, a method called proximity processing has been developed. In this situation no parser of the initial text is needed, and the system is based on semantical information of near words in sentences. The benefits are: easy implementation, portability between languages, robustness towards badly-formed sentences, and a sound representation using conceptual graphs.

Disambiguating proteins, genes, and RNA in text: a machine learning approach

“…However, in a practical application, the need for high specificity (low rate of false positives) in the output that the system extracts from the text often leads the system's designers to follow a knowledge intensive approach: Detailed models of human language processing, often in the form of a semantic grammar (Baud et al, 1992) (a grammar with both syntactic and classification information in its non-terminals), is painstakingly encoded by hand. The resulting system can then perform its task with an acceptably low error rate.…”

Compositionality: An Implementation Guide

“…Systems capable of understanding free speech are not presently available; however, many useful and reliable tools for the identifi cation and manipulation of strings, lexical structures, and concepts have been developed [13][14][15] . Although the potential of NLP is not fully realized, we believe that harnessing all available information inherent in a free-text input string is a strategic goal for electronic medical records.…”

Tensor-Based Semantically-Aware Topic Clustering of Biomedical Documents

“…PubMed abstracts are clustered with frequent words and near terms in [13]. A graph algorithm based on flow simulation is considered in [14], where advanced techniques are proposed in [15].…”