|
|
|
Foundation ::
Artificial Intelligence and Expert Systems ::
Qanda
|
Papers
This page gives you access to papers about Qanda and related research.
-
Information extraction from broadcast news speech data (
 PDF format, 53 K)
Abstract:
In this paper we describe a robust algorithm for information extraction from spoken language data. Our probabilistic algorithm builds on results in language modeling, using class-based smoothing to produce state-of-the-art performance for a wide range of speech error rates. We show that our system performs well with sparse data, as well as with out-of-domain data.
|
|
|
|
