Abstract
One of the main differences between Spoken Document Retrieval (SDR) systems and Text Retrieval systems is the need of a segmentation process that detects the story boundaries. However, until now, SDR researchers have not paid attention in building correct segments more than considering slidding windows of a fixed size in time. In this paper, new methodology for evaluating segments to SDR task, and the evaluation of three possible strategies are presented over the TREC-9 SDR collection. Moreover, the justification of each strategy is discussed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
The Ninth Text Retrieval Conference (TREC 9), Gaithersburg, Maryland (2000)
Llopis, F., Martínez-Barco, P.: Spoken Document Retrieval experiments with IR-n system. In: Proceedings of the CLEF 2003: Workshop on Cross-Language Information Retrieval and Evaluation, Trondheim, pp. 427–433 (2003)
Federico, M., Bertoldi, N., Levow, G.A., Jones, G.J.: CLEF 2004 Cross-Language Spoken Document Retrieval Track, 631–634
Johnson, S., Jourlin, P., Jones, K.S., Woodland, P.: Spoken Document Retrieval for TREC-9 at Cambridge University. In: [1], pp. 117–126
Renals, S., Abberley, D.: The Thisl SDR System at TREC-9. In: [1], pp. 627–634
Gauvain, J.L., Lamel, L., Barras, C., Adda, G., de Kercardio, Y.: The LIMSI SDR System for TREC-9. In: [1], pp. 335–360
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Terol, R.M., Martínez-Barco, P., Llopis, F., Martínez, T. (2005). An Application of NLP Rules to Spoken Document Segmentation Task. In: Montoyo, A., Muńoz, R., Métais, E. (eds) Natural Language Processing and Information Systems. NLDB 2005. Lecture Notes in Computer Science, vol 3513. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11428817_41
Download citation
DOI: https://doi.org/10.1007/11428817_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26031-8
Online ISBN: 978-3-540-32110-1
eBook Packages: Computer ScienceComputer Science (R0)