Entrepôts, Représentation et Ingénierie des Connaissances
Publications du laboratoire

Recherche approfondie

par Année
par Auteur
par Thème
par Type
- Readitopics: Make Your Topic Models Readable via Labeling and Browsing hal link

Auteur(s): Velcin J., Gourru A., Giry-Fouquet Erwan, Gravier Christophe, Roche Mathieu, Poncelet Pascal

Conference: IJCAI: International Joint Conference on Artificial Intelligence (Stockholm, SE, 2018-07-13)
Actes de conférence: 27th International Joint Conference on Artificial Intelligence, vol. p. (2018)

Ref HAL: lirmm-01910611_v1
Exporter : BibTex | endNote

Readitopics provides a new tool for browsing a textual corpus that showcases several recent work for labeling topic models and estimating topic coherence. We will demonstrate the potential of these techniques to get a deeper understanding of the topics that structure different kinds of datasets. This tool is provided as a Web demo but it can be easily installed to experiment with your own dataset. It can be further extended to deal with more advanced topic modeling techniques.