Accessing Information in Spoken Audio

April 19-20, 1999
Cambridge, UK

Task Dependent Loss Functions in Speech Recognition: Application to Named Entity Extraction

Vaibhava Goel and William Byrne

Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA

We present a risk-based decoding strategy for the task of Named Entity identification from speech. This approach does not select the most likely utterance produced by an ASR system, which would be the maximum a-posteriori (MAP) strategy, but instead chooses an utterance from an N-best list in an attempt to minimize the Bayes Risk under loss functions derived specifically for the Named Entity task. We describe our experimentation with three risk-based decoders corresponding to the following three performance evaluation criteria: the F-measure, the slot error rate, and the fraction of correctly identified reference slots. An unsupervised optimization is also applied to these decoders. The MAP decoder is used as the baseline for comparison. Our preliminary experiments with these task dependent decoders, using N-best lists of depth 200, show small but encouraging improvements in performance with respect to both manually tagged and machine tagged reference.

Full Paper (PDF)   Full Paper (Zipped Postscript)

Bibliographic reference.  Goel, Vaibhava / Byrne, William (1999): "Task dependent loss functions in speech recognition: application to named entity extraction", In Access-Audio-1999, 49-53.