• Aucun résultat trouvé

UEvora at CLEF eHealth 2017 Task 3

N/A
N/A
Protected

Academic year: 2022

Partager "UEvora at CLEF eHealth 2017 Task 3"

Copied!
5
0
0

Texte intégral

Références

Documents relatifs

Presence in ICD10 A binary feature that captures if the recognized entity features in the list of diseases included in the French version of the ICD10; the list was extracted from

For the recognized body part and age group terms, the recognized string and preferredString (extracted from UMLS) are added to the query and given extra weight (ˆ1.5) in the

Pseudo relevance feedback is used to improve retrieval results; this technique is used to obtain results that are originally returned from query to determine if

To deliver useful medical information, we at- tempted to combine multiple ranking methods, explicit semantic analysis (ESA), a clus- ter-based external expansion model

– Run1, Run2 and Run3, we translate the queries using Google Translate and then use Terrier’s implementation of DIR, PL2F, and LGD respectively.. – Run4 interpolates Run1, Run2 and

In detail, for each query, we use synonyms and hypernyms extracted from UMLS to produce alternative formulations (example in Table 1); then, we re- trieve results for each

To help laypeople, Conference and Labs of the Evaluation Forum (CLEF) launched the eHealth Evaluation Lab in 2013[1].The 2016 CLEF eHealth Task 3 Patient-Centred Information

In this paper we present the image classification techniques performed by the IPL Group for the subfigure classification subtask of ImageCLEF 2016 Medical Task.. For the