Thinking Outside the Box for Natural Language Processing

  • Srinivas Bangalore
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7181)


Natural Language Processing systems are often composed of a sequence of transductive components that transform their input into an output with additional syntactic and/or semantic labels. However, each component in this chain is typically error-prone and the error is magnified as the processing proceeds down the chain. In this paper, we present details of two systems, first, a speech driven question answering system and second, a dialog modeling system, both of which reflect the theme of tightly incorporating constraints across multiple components to improve the accuracy of their tasks.


Speech Recognition Natural Language Processing Speech Recognizer Search Accuracy Question Answering System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Acero, A., Bernstein, N., Chambers, R., Ju, Y., Li, X., Odell, J., Nguyen, P., Scholtz, O., Zweig, G.: Live search for mobile: Web services by voice on the cellphone. In: Proceedings of ICASSP 2008, Las Vegas (2008)Google Scholar
  2. 2.
    Alexandersson, J., Reithinger, N.: Learning dialogue structures from a corpus. In: Proceedings of Eurospeech (1997)Google Scholar
  3. 3.
    Allauzen, C., Mohri, M., Riley, M., Roark, B.: A generalized construction of speech recognition transducers. In: ICASSP, pp. 761–764 (2004)Google Scholar
  4. 4.
    Allauzen, C., Mohri, M., Roark, B.: Generalized algorithms for constructing statistical language models. In: Proceedings of ACL (2003)Google Scholar
  5. 5.
    Bacchiani, M., Beaufays, F., Schalkwyk, J., Schuster, M., Strope, B.: Deploying GOOG-411: Early lesstons in data, measurement and testing. In: Proceedings of ICASSP 2008, Las Vegas (2008)Google Scholar
  6. 6.
    Bangalore, S., DiFabbrizio, G., Stent, A.: Learning the structure of task-driven human-human dialog. IEEE Transactions on Audio, Speech, and Language Processing Special Issue on New Approaches to Statistical Speech and Text Processing 16(7), 1249–1259 (2008)Google Scholar
  7. 7.
    Bangalore, S., Fabbrizio, G.D., Stent, A.: Learning the structure of task-driven human-human dialogs. In: Proceedings of COLING/ACL (2006)Google Scholar
  8. 8.
    Bangalore, S., Stent, A.: Incremental parsing models for dialog task structure. In: Proceedings of the ACL (2009)Google Scholar
  9. 9.
    Grosz, B., Sidner, C.: Attention, intentions, and the structure of discourse. Computational Linguistics 12(3) (1986)Google Scholar
  10. 10.
    Hall, J., Nivre, J., Nilsson, J.: Discriminative classifiers for deterministic dependency parsing. In: Proceedings of COLING/ACL (2006)Google Scholar
  11. 11.
    Hatcher, E., Gospodnetic, O.: Lucene in Action. In Action series. Manning Publications Co., Greenwich (2004)Google Scholar
  12. 12.
    Lochbaum, K.: A collaborative planning model of intentional structure. Computational Linguistics 24(4), 525–572 (1998)Google Scholar
  13. 13.
    Mishra, T., Bangalore, S.: Finite-state models for speech-based search on mobile devices. Journal of Natural Language Engineering 17, 243–264 (2010)CrossRefGoogle Scholar
  14. 14.
    Mishra, T., Bangalore, S.: Qme!: A speech-based question-answering system on mobile devices. In: NAACL 2010 (2010)Google Scholar
  15. 15.
    Mohri, M., Pereira, F., Riley, M.: A Rational Design for a Weighted Finite-State Transducer Library. In: Wood, D., Yu, S. (eds.) WIA 1997. LNCS, vol. 1436, pp. 144–158. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  16. 16.
    Robertson, S.: Understanding inverse document frequency: On theoretical arguments for IDF. Journal of Documentation 60, 503–520 (2004)CrossRefGoogle Scholar
  17. 17.
    Sagae, K., Lavie, A.: A best-first probabilistic shift-reduce parser. In: Proceedings of COLING/ACL (2006)Google Scholar
  18. 18.
    Stent, A., Bangalore, S.: Incremental parsing models for dialog task structure. In: Proceedings of EACL (2009)Google Scholar
  19. 19.
  20. 20.
    Xu, W., Rudnicky, A.: Language modeling for dialog system. In: Proceedings of ICSLP (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Srinivas Bangalore
    • 1
  1. 1.AT&T Labs–ResearchFlorham ParkUSA

Personalised recommendations