Jihen Majdoubi

Using the Mesh Thesaurus to Index a Medical Article: Combination of Content, Structure and Semantics

This paper proposes an automatic method using a MeSH (Medical Subject Headings) thesaurus for generating a semantic annotation of medical articles. First, our approach uses NLP (Natural Language Processing) techniques to extract the indexing terms. Second, it extracts the Mesh concepts from this set of indexing terms. Then, these concepts are weighed based on their frequencies, locations in the article and their semantic relationships according to MeSH. Next, a refinement phase is triggered in order to upgrade the frequent ontologys concepts and determine the ones which will be integrated in the annotation. Finally, the structured result annotation is built.

An approach based on langage modeling for improving biomedical information retrieval

In the medical field, scientific articles represent a very important source of knowledge for researchers of this domain. But due to the large volume of scientific articles published on the web, an efficient detection and use of this knowledge is quite a difficult task. In this paper, we propose our contribution for conceptual indexing of medical articles by using the MeSH Medical Subject Headings thesaurus. With this in mind, we propose a tool for indexing medical articles called BIOINSY BIOmedical Indexing SYstem which uses a language model for selecting the best representative concepts for each document. The proposed indexing approach was evaluated by intensive experiments. These experiments were conducted on document test collections of real world clinical extracted from scientific collections, namely CISMEF and CLEF 2007. The results generated by these experiments demonstrate the effectiveness of our indexing approach.

Language Modeling for Medical Article Indexing

In the medical field, scientific articles represent a very important source of knowledge for researchers of this domain. But due to the large volume of scientific articles published on the web, an efficient detection and use of this knowledge is quite a difficult task.