Advertisement

From Off-line Evaluation to On-line Selection

  • Damir Ćavar
  • Uwe Küssner
  • Dan Tidhar
Part of the Artificial Intelligence book series (AI)

Abstract

In order to meet the challenges set by the innovative multi-engine translation architecture, an additional selection component is necessary. The selection component fulfills the task of integrating the various alternative translations that are produced for each input utterance, and comes up with exactly one optimal translation. In the center of this chapter is a learning method that was tailored to overcome the problem of incomparable confidence values delivered by the competing translation paths, thus enabling the selection component to rely on confidence values as the main selection criterion. By using off-line human feedback and applying a linear optimization heuristic, we determine a rescaling scheme that enables us to compare confidence values across modules. We also describe some additional information sources that further elaborate the selection procedure, and finally, outline some Quality of Service parameters that are supported by the selection module.

Keywords

Machine Translation Learning Cycle Translation Module Translation Quality Alternative Translation 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agmon, S. (1954). The Relaxation Method for Linear Inequalities. Canadian Journal of Mathematics, 6:382–392.MathSciNetMATHCrossRefGoogle Scholar
  2. Alexandersson, J., Buschbeck-Wolf, B., Fujinami, T., Kipp, M., Koch, S., Maier, E., Reithinger, N., Schmitz, B., and Siegel, M. (1997). Dialogue Acts in VERBMOBIL-2 Second Edition DFKI Saarbrücken, Universität Stuttgart, Technische Universität Berlin, Universität des Saarlandes, Verbmobil-Report 226.Google Scholar
  3. Amaldi, E., and Mattavelli, M. (1997). A Combinatorical Optimization Approach to Extract Piecewise Linear Structure from Nonlinear Data and an Application to Optical Flow Segmentation. TR 97–12, Cornell Computational Optimization Project, Cornell University, Ithaca NY, USA.Google Scholar
  4. Auerswald, M. Example-Based Machine Translation with Templates. In this volume. Google Scholar
  5. Batliner, A., Buckow, J., Niemann, H., Nöth, E., and Warnke, V. The Prosody Module. In this volume. Google Scholar
  6. Buschbeck-Wolf, B. (1997). Resolution on Demand. Universität Stuttgart. Verbmobil Report 196.Google Scholar
  7. Charniak, E., and Goldman, R. (1991). A Probabilistic Model of Plan Recognition. In Proceedings of the Ninth National Conference on Artificial Intelligence, 160–165.Google Scholar
  8. Cormen, T., Leiserson, C., and Rivet, L. (1989). Introduction to Algorithms. MIT Press, Cambridge, Massachusetts.Google Scholar
  9. Emele, M., and Dorna, M. (1998). Ambiguity Preserving Machine Translation using Packed Representations. In Proceedings of the 17th International Conference on Computational Linguistics (COLING-ACL ‘98), Montreal, Canada.Google Scholar
  10. Emele, M., Dorna, M., Ludeling, A., Zinsmeister, H., and Rohrer, C. Semantic-Based Transfer. In this volume. Google Scholar
  11. Endriss, U. (1998). Semantik zeitlicher Ausdrücke in Terminvereinbarungsdialogen. Verb-moil Report 227, TU Berlin.Google Scholar
  12. Frederking, R., and Nirenburg, S. (1994). Three Heads are Better than One. ANLP94P, 95–100.Google Scholar
  13. Heine, J., and Bos, J. Discourse and Dialogue Semantics for Translation. In this volume. Google Scholar
  14. Kilger A., and Finkler, W. (1995). Incremental Generation for Real-Time Applications. DFKI Report RR-95–11, DFKI GmbH.Google Scholar
  15. Kipp M., Alexandersson, J., and Reithinger, N. (1999). Understanding Spontaneous Negotiation Dialogue. In Proceedings of the IJCAI Workshop Knowledge and Reasoning in Practical Dialogue Systems Stockholm, Sweden.Google Scholar
  16. Kipp, M., Alexandersson, J., Reithinger, N., and Engel, R. Dialog Processing. In this volume. Google Scholar
  17. Koch, S., Küssner, U., Stede, M., and Tidhar, D. (2000). Contextual Reasoning in Speech-to-Speech Translation. In Proceedings of 2nd International Conference on Natural Language Processing (NLP2000). Springer LNAI.Google Scholar
  18. Koch, S., Küssner, U., and Stede, M. Contextual Disambiguation. In this volume. Google Scholar
  19. Küssner, U. (1997). Applying DL in Automatic Dialogue Interpreting. In Proceedings of the International Workshop on Description Logics (DL-97), Gif sur Yvette, France. 54–58.Google Scholar
  20. Küssner, U. (1998). Description Logic Unplugged. In Proceedings of the International Workshop on Description Logics (DL-98), Trento, Italy. 142–146.Google Scholar
  21. Motzkin, T.S., and Schoenberg, I.J. (1954). The Relaxation Method for Linear Inequalities. Canadian Journal of Mathematics, 6:393–404.MathSciNetMATHCrossRefGoogle Scholar
  22. Pfeifer, T., and Popescu-Zeletin, R.(1996). Generic Conversion of Communicating Media for Supporting Personal Mobility In Proceedings of the Third Cost 237 Workshop: Multimedia Telecommunications and Applications Google Scholar
  23. Rupp, C., Spilker, J., Klarner, M, and Worm, K. Combining Analyses from Various Parsers. In this volume. Google Scholar
  24. Schiehlen, M. Semantic Construction. In this volume. Google Scholar
  25. Schiehlen, M., Bos, J., and Dorna, M. Verbmobil Interface Terms (VITs). In this volume. Google Scholar
  26. Schmitz, B. (1997). Pragmatikbasiertes Maschinelles Dolmetschen. Dissertation, FB Informatik, TU Berlin, 1997.Google Scholar
  27. Schmitz, B., and Quantz, J.J. Dialogue Acts in Automatic Dialogue Interpreting. In Proceedings of the Sixth International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-95) Google Scholar
  28. Stede, M, Haas, S., and Küssner, U. (1998). Understanding and Tracking Temporal Descriptions in Dialogue. In Proceedings of KONVENS-98. Google Scholar
  29. Tessiore, L., and v. Hahn, W. Functional Validation of a Machine Interpretation System: Verbmobil. In this volume. Google Scholar
  30. Uszkoreit, H., Flickinger, D., Kasper, W., and Sag, I. Deep Linguistic Analysis with HPSG. In this volume. Google Scholar
  31. Vogel, S., Och, F.J., Tillmann, C., Niessen, S., Sawaf, H., and Ney, H. Statistical Methods for Machine Translation. In this volume. Google Scholar
  32. Worm C., and Rupp, C.J. (1998). Towards Robust Understanding of Speech by Combination of Partial Analyses In Proceedings of ECAI 1998 Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Damir Ćavar
    • 1
  • Uwe Küssner
    • 1
  • Dan Tidhar
    • 1
  1. 1.Technische Universität BerlinGermany

Personalised recommendations