Robust information extraction from automatically generated speech transcriptions

This paper describes a robust system for information extraction (IE) from spoken language data. The system extends previous hidden Markov model (HMM) work in IE, using a state topology designed for explicit modeling of variablelength phrases and class-based statistical language model smoothing to produce state-of-the-art performance for a wide range of speech error rates. Experiments on broadcast news data show that the system performs well with temporal and source di€erences in the data. In addition, strategies for integrating word-level con®dence estimates into the model are introduced, showing improved performance by using a generic error token for incorrectly recognized words in the training data and low con®dence words in the test data. Ó 2000 Elsevier Science B.V. All rights reserved.