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 variable-length 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 differences in the data. In addition, strategies for integrating word-level confidence 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 confidence words in the test data.

[1]  Mari Ostendorf,et al.  Transforming out-of-domain estimates to improve in-domain language models , 1997, EUROSPEECH.

[2]  Mitch Weintraub,et al.  Neural-network based measures of confidence for word recognition , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Scott W. Bennett,et al.  Learning to Tag Multilingual Texts Through Observation , 1997, EMNLP.

[4]  A. B.,et al.  SPEECH COMMUNICATION , 2001 .

[5]  George R. Krupka.  SRA: Description of the SRA System as Used for MUC-6 , 1995, MUC.

[6]  Victor Zue,et al.  Language modelling for recognition and understanding using layered bigrams , 1992, ICSLP.

[7]  Eric Brill,et al.  A corpus-based approach to language learning , 1993 .

[8]  R. J. Lickley,et al.  Proceedings of the International Conference on Spoken Language Processing. , 1992 .

[9]  Emmanuel Roche,et al.  Finite-State Language Processing , 1997 .

[10]  Richard M. Schwartz,et al.  Nymble: a High-Performance Learning Name-finder , 1997, ANLP.

[11]  Giuseppe Riccardi,et al.  How may I help you? , 1997, Speech Commun..

[12]  Douglas E. Appelt,et al.  NAMED ENTITY EXTRACTION FROM SPEECH: APPROACH AND RESULTS USING THE TEXTPRO SYSTEM , 1999 .

[13]  Steve Renals,et al.  Statistical annotation of named entities in spoken audio. , 1999 .

[14]  Eric Brill,et al.  A Simple Rule-Based Part of Speech Tagger , 1992, HLT.

[15]  Jan Robin Rohlicek,et al.  Statistical language modeling combining N-gram and context-free grammars , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  Ian H. Witten,et al.  The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compression , 1991, IEEE Trans. Inf. Theory.

[17]  Douglas E. Appelt,et al.  FASTUS: A Cascaded Finite-State Transducer for Extracting Information from Natural-Language Text , 1997, ArXiv.

[18]  Lynette Hirschman,et al.  Overview: Information Extraction From Broadcast News , 1999 .

[19]  Steve Renals,et al.  Integrated transcription and identification of named entities in broadcast speech , 1999, EUROSPEECH.

[20]  Heinrich Niemann,et al.  Probabilistic Semantic Analysis of Speech , 1997, DAGM-Symposium.

[21]  H. NiemannUniversit.  Semantigrams | Polygrams Detecting Meaning , 1997 .

[22]  Lynette Hirschman,et al.  MITRE: Description of the Alembic System Used for MUC-6 , 1995, MUC.

[23]  Steve Renals,et al.  Named entity tagged language models , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[24]  Mari Ostendorf,et al.  INFORMATION EXTRACTION FROM BROADCAST NEWS SPEECH DATA , 1999 .

[25]  Ralph Weischedel,et al.  Named Entity Extraction from Broadcast News , 1999 .

[26]  Lynette Hirschman,et al.  Named Entity Scoring for Speech Input , 1998, COLING-ACL.

[27]  Beth Sundheim,et al.  MUC-5 Evaluation Metrics , 1993, MUC.

[28]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[29]  Herbert Gish,et al.  Improved estimation, evaluation and applications of confidence measures for speech recognition , 1997, EUROSPEECH.

[30]  Thomas Schaaf,et al.  Estimating confidence using word lattices , 1997, EUROSPEECH.

[31]  Larry Gillick,et al.  A probabilistic approach to confidence estimation and evaluation , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[32]  Mark Stevenson,et al.  BASELINE IE-NE EXPERIMENTS USING THE SPRACH/LASIE SYSTEM , 1999 .