Named Entity Recognition in Speech Transcripts following an Extended Taxonomy
Abstract
In this paper, we present a French named entity recognition (NER) system that was first developed as part of our participation in the ETAPE 2012 evaluation campaign and then extended to cover more entity types. The ETAPE 2012 evaluation campaign considers an hierarchical and compositional taxonomy that makes the NER task more complex. We present a multi-level methodology based on conditional random fields (CRFs). With respect to existing systems, our methodology allows a fine-grained annotation. Experiments were conducted using the manually annotated training and evaluation corpora provided by the organizers of the campaign. The obtained results are presented and discussed.