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.
%0 Conference Paper
%1 Surdeanu:2005
%A Surdeanu, Mihai
%A Turmo, Jordi
%A Comelles, Eli
%B Proceedings Interspeech-05
%C Lisbon
%D 2005
%K named_entities speech
%T Named Entity Recognition from Spontaneous Open-Domain Speech
%U http://www.lsi.upc.edu/~comelles/
%X 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.
@inproceedings{Surdeanu:2005,
abstract = {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.},
added-at = {2007-12-14T02:47:08.000+0100},
address = {Lisbon},
author = {Surdeanu, Mihai and Turmo, Jordi and Comelles, Eli},
biburl = {https://www.bibsonomy.org/bibtex/22b0790ca9fa1c810363f5df441fc1254/diego_ma},
booktitle = {Proceedings Interspeech-05},
interhash = {5c1e7cca18b3a3a40a8456f8bbf44519},
intrahash = {2b0790ca9fa1c810363f5df441fc1254},
keywords = {named_entities speech},
timestamp = {2007-12-14T02:47:08.000+0100},
title = {Named Entity Recognition from Spontaneous Open-Domain Speech},
url = {http://www.lsi.upc.edu/~comelles/},
year = 2005
}