UNIGE document Scientific Article
previous document  unige:146795  next document
add to browser collection
Title

Evaluation of Document Retrieval Systems on a Medical Corpus in French: Indexation vs. Feature Learning

Authors
Damachi, Francis
Published in Studies in Health Technology and Informatics. 2020, vol. 270, p. 208-212
Abstract This paper presents five document retrieval systems for a small (few thousands) and domain specific corpora (weekly peer-reviewed medical journals published in French) as well as an evaluation methodology to quantify the models performance. The proposed methodology does not rely on external annotations and therefore can be used as an ad hoc evaluation procedure for most document retrieval tasks. Statistical models and vector space models are empirically compared on a synthetic document retrieval task. For our dataset size and specificities the statistical approaches consistently performed better than its vector space counterparts.
Keywords HumansInformation Storage and Retrieval/methodsLanguageMedical Subject HeadingsModels, StatisticalNatural Language Processing
Identifiers
PMID: 32570376
Full text
Article (Published version) (280 Kb) - public document Free access
Structures
Research group Interfaces Homme-machine en milieu clinique (610)
Citation
(ISO format)
ROBERT, Arnaud et al. Evaluation of Document Retrieval Systems on a Medical Corpus in French: Indexation vs. Feature Learning. In: Studies in Health Technology and Informatics, 2020, vol. 270, p. 208-212. doi: 10.3233/SHTI200152 https://archive-ouverte.unige.ch/unige:146795

95 hits

22 downloads

Update

Deposited on : 2020-12-18

Export document
Format :
Citation style :