Bibtex de la publication

@InProceedings{ DiTa2011.1,
author = {Dinh, Duy and Tamine, Lynda},
title = "{Biomedical concept extraction based on combining the content-based and word order similarities (regular paper)}",
booktitle = "{ACM Symposium on Applied Computing (SAC 2011), Taichung, Taiwan, 21/03/11-25/03/11}",
year = {2011},
month = {mars},
publisher = {ACM : Association for Computing Machinery},
address = {},
pages = {1159--1163},
language = {anglais},
URL = {},
keywords = {Concept Recognition, Semantic Indexing, Document Expansion, Biomedical Information Retrieval},
note = {full paper, acceptance rate : 30\% = 239/790},
abstract = {It is well known that the main objective of conceptual retrieval models is to go beyond simple term matching by relaxing term independence assumption through concept recognition. In this paper, we present an approach of semantic indexing and retrieval of biomedical documents through the process of identifying domain concepts extracted from the Medical Subject Headings (MeSH) thesaurus. Our indexing approach relies on a purely statistical vector space model, which represents medical documents and MeSH concepts as term vectors. By leveraging a combination of the bag-of-word concept representation and word positions in the textual features, we demonstrate that our mapping method is able to extract valuable concepts from documents. The output of this semantic mapping serves as the input to our relevance document scoring in response to a query. Experiments on the OHSUMED collection show that our semantic indexing method significantly outperforms state-of-art baselines that employ word or term statistics.}