We present an automated system for assigning protein, gene, or mRNA class labels to biological terms in free text. Three machine learning algorithms and several extended ways for defining contextual features for disambiguation are examined, and a fully unsupervised manner for obtaining training examples is proposed. We train and evaluate our system over a collection of 9 million words of molecular biology journal articles, obtaining accuracy rates up to 85%.

Abstract not found

This paper is organized as follows. First, we start with a brief recall of basic notions and related literature. Second, we describe the structuration of knowledge in Menelas, and the way it rests on a CTL. Third, we show how UMLS has been used to initiate CTL building, then illustrate how the CTL structures the knowledge acquisition process. Finally, we discuss the advantages and further issues associated with this approach.

The elicitation of the ontology -- i.e. the objects of a domain -- is a key issue of conceptual modelling and therefore of knowledge acquisition. The Conceptual Graph Theory provides a knowledge representation formalism to be used in knowledgebased systems with an explicit "type lattice" to account for the ontology. Since knowledge is in most AI applications non formal, it has to be normalized to ensure that the formal exploitation of its representation conforms to its meaning in the domain. Noting the intensional nature of types, which reflect the essences of the objects they denote, this normalization relies on a commitment on type definitions by necessary and sufficient conditions at the knowledge level. Our claim is that the taxonomic structure that accounts for the intensional nature of the ontology can be nothing but a tree, precluding tangled taxonomies. From this starting point, we derive methodological principles to constrain the acquisition of the "type tree", thus...

The overall goal of Menelas is to provide better access to the information contained in natural language patient discharge summaries, through the design and implementation of a pilot system able to access medical reports through natural languages. A first, experimental version of the Menelas indexing prototype for French has been assembled. Its function is to encode free text PDSs into both an internal representation and ICD-9-CM nomenclature codes. A preliminary evaluation shows the potential for reasonable coverage and precision. The Menelas prototype will be enhanced and extended into a pilot system which will be tested in two hospital sites. Keywords: Natural Language Processing; Patient Record; Knowledge-Based Systems; Information Retrieval; ICD-9-CM; Conceptual Graphs.

this paper, we examine some methodological and theoretical principles to enforce this conformity. These principles result from our experience in Menelas, a medical language understanding project.

The theory of conceptual structures serves as a common basis for natural language processing and medical concept representation. We present a PROLOG-based formalization of dependency grammar that can accommodate conceptual structures in its dependency rules. First results indicate that this formalization provides an operational basis for the implementation of medical language parsers and for the design of medical concept representation languages.

The automatic analysis of medical full-texts currently suffers from neglecting text coherence phenomena such as reference relations between discourse units. This has unwarranted effects on the descriptional adequacy of medical knowledge bases automatically generated from texts. The resulting representation bias can be characterized in terms of artificially fragmented, incomplete and invalid knowledge structures. We discuss three types of textual phenomena (pronominal and nominal anaphora, as well as textual ellipsis) and outline basic methodologies how to deal with them. Keywords: natural language processing, pathology Introduction With the overall diffusion of electronic text processing technology in clinical offices and at the physician's workplace, and, more recently, the unlimited access to text resources in the Internet, a vast potential for medical information supply arises. The natural language processing community has responded to the urgent needs of real-world text process...

We have examined a number of methods for structuring and processing free text documents including formal concept analysis, knowledge spaces, and conceptual graphs. Lattice structures over documents has been previously shown to be efficient and effective for information retrieval. We propose to integrate concept analysis, knowledge spaces and self-organisation in general and apply these methods to patient discharge summaries. We intend to demonstrate that a combination of conceptual graph representation of medical texts and document clustering techniques can provide efficient information retrieval and at the same time improve the quality of information returned to users. 1 Introduction When paper medical records are examined in detail, the types of data they contain can be broadly classified into two main categories: structured data and unstructured data. Unstructured data in the form of natural language forms a larger portion of the medical record [SBS + 82] because it is the medium...

We present a neural network based approach to the extraction of information from a medical database. Medical concepts are encoded by using conceptual graphs, which have been demonstrated useful for this purpose. The medical conceptual graphs are encoded into a paticular neural network architecture, i.e., the Labeling RAAM, which allows the processing of structures both using pointers (reduced descriptors) and by content. Associative queries to the database are implemented by Generalized Hopfield Networks, which are generated `on the fly' by opportunely composing the weights of the LRAAM. Complex concepts are retrieved starting from basic or partial concepts conveyed by medical sentences.