Confidence measures for semi-automatic labeling of dialog acts - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Confidence measures for semi-automatic labeling of dialog acts


This paper deals with semi-supervised classifier training for automatic Dialog Acts (DAs) recognition. In our previous works, we have designed a dialog act recognition system for reservation applications in the Czech language. In this work, we propose to retrain this system on another corpus, for another task (broadcast news speech), in a different language (French) and with another set of dialog acts. This is realized using a semi-supervised approach based on the Expectation-Maximization (EM) algorithm. We show that, in the proposed experimental setup, the use of confidence measures to filter out incorrectly recognized dialog acts is required to improve the results. Two confidence measures are thus proposed and evaluated on the French broadcast news corpus. Experimental results confirm the interest of this approach for the task of training automatic dialog act classifiers.
No file

Dates and versions

inria-00184469 , version 1 (31-10-2007)


  • HAL Id : inria-00184469 , version 1


Pavel Kral, Christophe Cerisara, Jana Kleckova. Confidence measures for semi-automatic labeling of dialog acts. IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP 2007, Apr 2007, Honolulu, United States. ⟨inria-00184469⟩
114 View
0 Download


Gmail Facebook Twitter LinkedIn More