%0 Conference Paper %F Poster %T A semi-supervised Learning Approach to find equivalent long-string Organization Names %+ École des Ponts ParisTech (ENPC) %+ Laboratoire Interdisciplinaire Sciences, Innovations, Sociétés (LISIS) %A Bordignon, Frédérique %A Turenne, Nicolas %A Feugueur, Yann %< avec comité de lecture %B Colloque- Forum PEPS EXIA %C Champs sur Marne, France %8 2016-10-11 %D 2016 %Z Humanities and Social Sciences/Library and information sciences %Z Humanities and Social Sciences/Linguistics %Z Computer Science [cs]/Document and Text ProcessingConference poster %X Background: A platform called Opalia has been built to propose free access to all publications about a laboratory for a given range of years. This platform makes indexing of a corpus of a scientific article of a given lab. But in the French research system, a lab includes researchers from different organizations in the same unit generally called. UMR. Authors can write their laboratory names differently. Aim: Sorting a set of labels that is noisy can be seen as a binary classification into positives and leave negatives strings. We propose to use a cascade processing with the help of tagging some positive strings to build a relevant space of features that helps classification into good labels. %G English %2 https://enpc.hal.science/hal-02310298/document %2 https://enpc.hal.science/hal-02310298/file/poster_EXIA_v1.pdf %L hal-02310298 %U https://enpc.hal.science/hal-02310298 %~ SHS %~ ENPC %~ CNRS %~ INRA %~ AO-LINGUISTIQUE %~ PARISTECH %~ LISIS %~ AGREENIUM %~ INRAE %~ UNIV-EIFFEL %~ UPEM-UNIVEIFFEL %~ ESIEE-UNIVEIFFEL