Jeremy G. Kahn
ABSTRACT
The lack of sentence boundaries and presence of disfluencies pose difficulties for parsing conversational speech. This work investigates the effects of automatically detecting these phenomena on a probabilistic parser's performance. We demonstrate that a state-of-the-art segmenter, relative to a pause-based segmenter, gives more than 45% of the possible error reduction in parser performance, and that presentation of interruption points to the parser improves performance over using sentence boundaries alone.
- E. Black et al. 1991. A procedure for quantitatively comparing syntactic coverage of English grammars. In Proc. 4th DARPA Speech&Natural Lang. Workshop, pages 306--311. Google Scholar
Digital Library
- E. Charniak and M. Johnson. 2001. Edit detection and parsing for transcribed speech. In Proc. 2nd NAACL, pages 118--126. Google ScholarDigital Library
- C. Chelba and F. Jelinek. 2000. Structured language modeling. Computer Speech and Language, 14(4):283--332, October.Google ScholarDigital Library
- M. Core and K. Schubert. 1999. Speech repairs: A parsing perspective. In Satellite Meeting ICPHS 99.Google Scholar
- J. Huang and G. Zweig. 2002. Maximum entropy model for punctuation annotation from speech. In Proc. Eurospeech.Google Scholar
- J.-H. Kim and P. Woodland. 2001. The use of prosody in a combined system for punctuation generation and speech recognition. In Proc. Eurospeech, pages 2757--2760.Google Scholar
- J. Kim, S. E. Schwarm, and M. Ostendorf. 2004. Detecting structural metadata with decision trees and transformation-based learning. In Proc. HLT-NAACL.Google Scholar
- Y. Liu, E. Shriberg, and A. Stolcke. 2003. Automatic disfluency identification in conversational speech using multiple knowledge sources. In Proc. Eurospeech, volume 1, pages 957--960.Google Scholar
- L. Mayfield et al. 1995. Parsing real input in JANUS: a concept-based approach. In Proc. TMI 95.Google Scholar
- NIST. 2003. Rich Transcription Fall 2003 Evaluation Results. http://www.nist.gov/speech/tests/rt/rt2003/fall/.Google Scholar
- S. Sekine and M. Collins. 1997. EVALB. As in Collins ACL 1997; http://nlp.cs.nyu.edu/evalb/.Google Scholar
- S. Strassel, 2003. Simple Metadata Annotation Specification V5.0. Linguistic Data Consortium.Google Scholar
- Parsing conversational speech using enhanced segmentation
Recommendations
LLLR parsing
SAC '13: Proceedings of the 28th Annual ACM Symposium on Applied ComputingThe idea of an LLLR parsing is presented. An LLLR(k) parser can be constructed for any LR(k) grammar but it produces the left parse of the input string in linear time (in respect to the length of the derivation) without backtracking. If used as a basis ...
Interactive Translation of Conversational Speech
Speech recognition performance has come a long way in the past 10 years. Present technology permits speaker-independent, continuous-speech, large-vocabulary dictation systems with word error rates of about 10 percent. Machine translation has also ...
Comments