Abstract
Within the machine translation project Verbmobil, translation is performed simultaneously along four independent translation paths, each implementing a different MT strategy. The four competing translations are combined by a selection procedure so as to form a single optimized output for each input utterance. This selection procedure relies on confidence values that are delivered together with each of the alternative translations. Since the confidence values are computed by four independent modules that are fundamentally different from one another, they are not directly comparable and need to be rescaled in order to gain comparative significance. In this paper we describe a machine learning method tailored to overcome this difficulty by using off line human feedback to determine an optimized confidence rescaling scheme.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alexandersson, J., Buschbeck-Wolf, B., Fujinami, T., Kipp, T., Koch, S., Maier, E., Reithinger, N., Schmitz, B., Siegel, M.: Dialogue Acts in VERBMOBIL-2 Second Edition. DFKI Saarbrücken, Universität Stuttgart, Technische Universität Berlin, Universität des Saarlandes, Verbmobil-Report 226 (1997)
S.Agmon, S.: The relaxation method for linear inequalities. Canadian Journal of Mathematics, 6 (1954) 382–392
Amaldi, E. Mattavelli, M.: 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 (1997)
Buckow, J., Batliner, A., Gallwitz, F., Huber, R., Nöth, E., Warnke, V., Niemann H.: Dovetailing of Acoustics and Prosody in Spontaneous Speech Recognition. Proc. Int. Conf. on Spoken Language Processing, volume 3, Sydney, Australia (1998) 571–574
Buschbeck-Wolf, B. Resolution on Demand. Universität Stuttgart. Verbmobil-Report 196 (1997)
Cormen, T., Leiserson, C. Rivet, L.: Introduction to Algorithms. MIT Press, Cambridge, Massachusetts (1989)
Dorna, M.: The ADT Package for the Verbmobil Interface Term.. Universität Stuttgart, Verbmobil-Report 104X (1999)
Emele, M. Dorna, M.: Efficient Implementation of a Semantic-based Transfer Approach. Proceedings of the 12th European Conference on Artificial Intelligence (ECAI-96) (1996)
Emele, M., Dorna, M.: Ambiguity Preserving Machine Translation using Packed Representations. Proceedings of the 17th International Conference on Computational Linguistics (COLING-ACL’ 98), Montreal, Canada (1998)
Endriss, U.: Semantik zeitlicher Ausdrücke in Terminvereinbarungsdialogen. Technische Universität Berlin, Verbmobil-Report 227 (1998)
Frederking, R., Nirenburg, S.: Three Heads are Better than One. ANLP94P (1994) 95–100
Kilger, A., Finkler, W.: Incremental Generation for Real-Time Applications. DFKI Report RR-95-11, German Research Center for Artificial Intelligence-DFKI GmbH (1995)
Kipp, M., Alexandersson, J., Reithinger, N.: Understanding Spontaneous Negotiation Dialogue. Proceedings of the IJCAI Workshop Knowledge and Reasoning in Practical Dialogue Systems. Stockholm, Sweden (1999)
Koch, S., Küssner, U., Stede, M., Tidhar D.: Contextual reasoning in speech-to-speech translation. Proceedings of 2nd International Conference on Natural Language Processing (NLP2000), Springer Lecture Notes in Artificial Intelligence (2000)
Küssner, U.: Applying DL in Automatic Dialogue Interpreting. Proceedings of the International Workshop on Description Logics-DL-97, Gif sur Yvette, France (1997) 54–58
Küssner, U.: Description Logic Unplugged. Proceedings of the International Workshop on Description Logics-DL-98, Trento, Italy (1998) 142–146
Och, F.J., Tillmann, C., Ney, N.: Improved Alignment models for Statistical Machine Translation. Proceedings of the Joint SIGDAT Conf. on Empirical Methods in Natural Language Processing and Very Large Corpora, University of Maryland (1999)
Motzkin, T.S., Schoenberg, I.J.: The relaxation method for linear inequalities. Canadian Journal of Mathematics, 6 (1954) 393–404
Ruland, T., Rupp, C.J., Spilker, J., Weber, H., Worm C.: Making the Most of Multiplicity: A Multi-Parser Multi-Strategy Architecture for the Robust Processing of Spoken Language. Proceedings of ICSLP (1998)
Schmitz, B. Pragmatikbasiertes Maschinelles Dolmetschen. Dissertation, FB Informatik, Technische Universität Berlin (1998)
Schmitz, B. Quantz, J.J.: Dialogue Acts in Automatic Dialogue Interpreting. Proceedings of the Sixth International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-95), Leuven (1995)
Stede, M., Haas, S., Küssner U.: Understanding and tracking temporal descriptions in dialogue. Proceedings of KONVENS-98, Bonn (1998)
Wahlster, W.: Verbmobil: Translation of face-to-face dialogues. Proceedings of the Third European Conference of Speech Communication and Technology. Berlin (1993)
Worm, C., Rupp, C.J.: Towards Robust Understanding of Speech by Combination of Partial Analyses. Proceedings of ECAI (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Küssner, U., Tidhar, D. (2000). Combining Different Translation Sources. In: Christodoulakis, D.N. (eds) Natural Language Processing — NLP 2000. NLP 2000. Lecture Notes in Computer Science(), vol 1835. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45154-4_25
Download citation
DOI: https://doi.org/10.1007/3-540-45154-4_25
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67605-8
Online ISBN: 978-3-540-45154-9
eBook Packages: Springer Book Archive