emnlp emnlp2013 emnlp2013-116 emnlp2013-116-reference knowledge-graph by maker-knowledge-mining

116 emnlp-2013-Joint Parsing and Disfluency Detection in Linear Time


Source: pdf

Author: Mohammad Sadegh Rasooli ; Joel Tetreault

Abstract: We introduce a novel method to jointly parse and detect disfluencies in spoken utterances. Our model can use arbitrary features for parsing sentences and adapt itself with out-ofdomain data. We show that our method, based on transition-based parsing, performs at a high level of accuracy for both the parsing and disfluency detection tasks. Additionally, our method is the fastest for the joint task, running in linear time.


reference text

Miguel Ballesteros and Joakim Nivre. 2013. Going to the roots of dependency parsing. Computational Linguistics, 39(1):5–13. Heather Bortfeld, Silvia D. Leon, Jonathan E. Bloom, Michael F. Schober, and Susan E. Brennan. 2001. Disfluency rates in conversation: Effects of age, relationship, topic, role, and gender. Language and Speech, 44(2): 123–147. Eugene Charniak and Mark Johnson. 2001. Edit detec- tion and parsing for transcribed speech. In NAACLHLT, pages 1–9. Michael Collins. 2002. Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In ACL, pages 1–8. Ian R. Finlayson and Martin Corley. 2012. Disfluency in dialogue: an intentional signal from the speaker? Psychonomic bulletin & review, 19(5):921–928. Kallirroi Georgila. 2009. Using integer linear programming for detecting speech disfluencies. In NAACLHLT, pages 109–1 12. John J. Godfrey, Edward C. Holliman, and Jane McDaniel. 1992. Switchboard: Telephone speech corpus for research and development. In ICASSP, volume 1, pages 517–520. Mark Johnson and Eugene Charniak. 2004. A tag-based noisy channel model of speech repairs. In ACL, pages 33–39. Jeremy G. Kahn, Matthew Lease, Eugene Charniak, Mark Johnson, and Mari Ostendorf. 2005. Effective use of prosody in parsing conversational speech. In EMNLP, pages 233–240. Matthew Lease and Mark Johnson. 2006. Early deletion of fillers in processing conversational speech. In NAACL-HLT, pages 73–76. Roger Levy and Galen Andrew. 2006. Tregex and tsurgeon: tools for querying and manipulating tree data structures. In LREC, pages 223 1–2234. Tim Miller and William Schuler. 2008. A unified syntactic model for parsing fluent and disfluent speech. In ACL-HLT, pages 105–108. Christine Nakatani and Julia Hirschberg. 1993. A speech-first model for repair detection and correction. In ACL, pages 46–53. Joakim Nivre, Johan Hall, Jens Nilsson, Atanas Chanev, G ¨ulsen Eryigit, Sandra K ¨ubler, Svetoslav Marinov, and Erwin Marsi. 2007. Maltparser: A languageindependent system for data-driven dependency parsing. Natural Language Engineering, 13(2):95–135. Joakim Nivre. 2004. Incrementality in deterministic dependency parsing. In the Workshop on Incremental Parsing: Bringing Engineering and Cognition Together, pages 50–57. 129 Joakim Nivre. 2008. Algorithms for deterministic incremental dependency parsing. Computational Linguistics, 34(4):513–553. Xian Qian and Yang Liu. 2013. Disfluency detection using multi-step stacked learning. In NAACL-HLT, pages 820–825. Wen Wang, Andreas Stolcke, Jiahong Yuan, and Mark Liberman. 2013. A cross-language study on automatic speech disfluency detection. In NAACL-HLT, pages 703–708. Yue Zhang and Joakim Nivre. 2011. Transition-based dependency parsing with rich non-local features. In ACL (Short Papers), pages 188–193. Simon Zwarts and Mark Johnson. 2011. The impact of language models and loss functions on repair disfluency detection. In ACL, pages 703–71 1.