We focus in this paper on the named entity recognition task in spoken data. The proposed approach investigates the use of various contexts of the words to improve recognition. Experimental results carried out on speech data from French broadcast news, using conditional random fields (CRF) show that the use of semantic information, generated using symbolic analyzer outperform the classical approach in reference transcriptions, and it is more robust in automatic speech recognition (ASR) output.
Bibliographic reference. Zidouni, Azeddine / Rosset, Sophie / Glotin, Hervé (2010): "Efficient combined approach for named entity recognition in spoken language", In INTERSPEECH-2010, 1293-1296.