%0 Conference Proceedings %T United we stand: Using multiple strategies for topic labeling %+ Entrepôts, Représentation et Ingénierie des Connaissances (ERIC) %+ Territoires, Environnement, Télédétection et Information Spatiale (UMR TETIS) %+ Laboratoire Hubert Curien (LHC) %+ ADVanced Analytics for data SciencE (ADVANSE) %A Gourru, Antoine %A Velcin, Julien %A Roche, Mathieu %A Gravier, Christophe %A Poncelet, Pascal %< avec comité de lecture %( 23rd International Conference on Applications of Natural Language to Information Systems %B NLDB: Natural Language Processing and Information Systems %C Paris, France %V LNCS %N 10859 %P 352-363 %8 2018-06-13 %D 2018 %R 10.1007/978-3-319-91947-8_37 %Z Computer Science [cs]/Databases [cs.DB]Conference papers %X Topic labeling aims at providing a sound, possibly multi-words, label that depicts a topic drawn from a topic model. This is of the utmost practical interest in order to quickly grasp a topic informa-tional content-the usual ranked list of words that maximizes a topic presents limitations for this task. In this paper, we introduce three new unsupervised n-gram topic labelers that achieve comparable results than the existing unsupervised topic labelers but following different assumptions. We demonstrate that combining topic labelers-even only two-makes it possible to target a 64% improvement with respect to single topic labeler approaches and therefore opens research in that direction. Finally, we introduce a fourth topic labeler that extracts representative sentences, using Dirichlet smoothing to add contextual information. This sentence-based labeler provides strong surrogate candidates when n-gram topic labelers fall short on providing relevant labels, leading up to 94% topic covering. %G English %2 https://hal-lirmm.ccsd.cnrs.fr/lirmm-01910614/document %2 https://hal-lirmm.ccsd.cnrs.fr/lirmm-01910614/file/NLDB_Julien.pdf %L lirmm-01910614 %U https://hal-lirmm.ccsd.cnrs.fr/lirmm-01910614 %~ UNIV-ST-ETIENNE %~ CIRAD %~ IOGS %~ AGROPARISTECH %~ CNRS %~ UNIV-LYON1 %~ UNIV-LYON2 %~ IRSTEA %~ PARISTECH %~ ERIC %~ ADVANSE %~ LIRMM %~ AGROPOLIS %~ TETIS %~ AGREENIUM %~ MIPS %~ UNIV-MONTPELLIER %~ LYON2 %~ UDL %~ UNIV-LYON %~ INRAE %~ INRAEOCCITANIEMONTPELLIER %~ UM-2015-2021 %~ TEST3-HALCNRS %~ TEST4-HALCNRS %~ MATHNUM %~ TEST5-HALCNRS