This paper presents an analysis of named entity recognition and classification in spontaneous speech transcripts. We annotated a significant fraction of the Switchboard corpus with six named entity classes and investigated a battery of machine learning models that include lexical, syntactic, and semantic attributes. The best recognition and classification model obtains promising results, approaching within 5% a system evaluated on clean textual data.
Cite as: Surdeanu, M., Turmo, J., Comelles, E. (2005) Named entity recognition from spontaneous open-domain speech. Proc. Interspeech 2005, 3433-3436, doi: 10.21437/Interspeech.2005-306
@inproceedings{surdeanu05_interspeech,
author={Mihai Surdeanu and Jordi Turmo and Eli Comelles},
title={{Named entity recognition from spontaneous open-domain speech}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={3433--3436},
doi={10.21437/Interspeech.2005-306}
}