@ARTICLE{10.21494/ISTE.OP.2018.0208, TITLE={Document vector embeddings for bibliographic records indexing}, AUTHOR={Morgane Marchand, Geoffroy Fouquier, Emmanuel Marchand, Guillaume Pitel, }, JOURNAL={Information Retrieval, Document and Semantic Web}, VOLUME={1}, NUMBER={Issue 1}, YEAR={2018}, URL={https://openscience.fr/Document-vector-embeddings-for-bibliographic-records-indexing}, DOI={10.21494/ISTE.OP.2018.0208}, ISSN={2516-3280}, ABSTRACT={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.}}