TY  - Type of reference 
TI  - Document vector embeddings for bibliographic records indexing 
AU  - Morgane Marchand 
AU  - Geoffroy Fouquier 
AU  - Emmanuel Marchand 
AU  - Guillaume Pitel 
AB  - This article presents the eXenSa contribution to the 2016 DEFT shared task. The proposed task consists in indexing
bibliographic records with keywords chosen by professional indexers. We propose a statistical approach which combines graphical and
semantic approaches. The first approach defines a document keywords as thesaurus terms graphically similar to terms contained in
the title or the abstract of this document. The second approach assigns to document the keywords associated with semantically similar
documents in training corpora. Both approaches use vector space models generated using NC-ISC, a stochastic matrix factorisation
algorithm. Our system obtains the best F-score on half of the four test corpora and ranks second for the two others. 
DO  - 10.21494/ISTE.OP.2018.0208 
JF  - Information Retrieval, Document and Semantic Web 
KW  - Indexation,  keywords,  semantic spaces,  word vector embedding, Indexation,  mots-clefs,  espaces sémantiques,  représentation vectorielle de mots,  
L1  - https://openscience.fr/IMG/pdf/iste_ridows17v1n4.pdf 
LA  - en 
PB  - ISTE OpenScience 
DA  - 2018/01/9 
SN  - 2516-3280 
TT  - Représentation vectorielle de documents pour l’indexation de notices bibliographiques 
UR  - https://openscience.fr/Document-vector-embeddings-for-bibliographic-records-indexing 
IS  - Issue 1 
VL  - 1 
ER  -