Skip to main content
SpringerLink
Log in

Der statistische Ansatz in der maschinellen Sprachverarbeitung

  • Chapter
Sprache zwischen Theorie und Technologie / Language between Theory and Technology

Part of the book series: Sprachwissenschaft ((SPRAWI))

  • 426 Accesses

Zusammenfassung

Dieser Beitrag behandelt die Rolle des statistischen Ansatzes in der maschinellen (oder automatischen) Sprachverarbeitung. Der statistische Ansatz bietet folgende Vorteile: 1) leistungsfähige Kriterien und Konzepte für das automatische Training der Modell-parameter aus Beispieldaten, 2) ein globales Entscheidungskriterium, das nach den Regeln der statistischen Entscheidungstheorie die Zahl der Fehlentscheidungen mini-miert. Diese Eigenschaften spielen gerade in der Sprachverarbeitung eine wichtige Rolle, da die Regeln nicht in einer expliziten Form vorliegen — unabhängig von der Frage, ob es diese Regeln überhaupt gibt.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 74.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

Literatur

  • Alshawi, H. und F. Xiang. 1997. English-to-Mandarin Speech Translation with Head Transducers. In: Proc. Spoken Language Translation Workshop, ACL 1997, Madrid. 54–60.

    Google Scholar 

  • Auerswald, M. 2000. Example-based Machine Translation with Templates. In: Wahlster ( 2000 ), 418–427.

    Google Scholar 

  • Aust, H. und H. Ney. 1998. Evaluating Dialog Systems Used in the Real World. In: Proc. IEEE Int, Conf. on Acoustics, Speech and Signal Processing, Seattle, WA. 1053–1056.

    Google Scholar 

  • Berger, A. L., P. F. Brown, J. Cocke, S. A. Della Pietra, V. J. Della Pietra, J. R. Gillett, J. Lafferty, R. L. Mercer, H. Printz und L. Ures. 1994. The Candide System for Machine Translation. In: Proc. ARPA Human Language Technology Workshop, Plainsboro, N.J. 152–157.

    Google Scholar 

  • Block, U. 2000. Example-based Incremental Synchronous Interpretation. In: Wahlster ( 2000 ), 411–417.

    Google Scholar 

  • Breiman, L., J. H. Friedman, R. A. Ohlson und C. J. Stone. 1984. Classification And Regression Trees. Belmont, CA: Wadsworth.

    Google Scholar 

  • Brown, P. F., J. Cocke, S. A. Delia Pietra, V. J. Della Pietra, F. Jelinek, J. D. Lafferty, R. L. Mercer und P. S. Roossin. 1990. A Statistical Approach to Machine Translation. Computational Linguistics 16 (2): 79–85.

    Google Scholar 

  • Brown, P. F., S. A. Delia Pietra, V. J. Delia Pietra und R. L. Mercer. 1993. Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics 19 (2): 263–311.

    Google Scholar 

  • Chomsky, N. 1969. Quine’s Empirical Assumptions. In: D. Davidson und J. Hintikka (Hg.). Words and Objections. Essays on the Work of W. V. Quine. Dordrecht: Reidel.

    Google Scholar 

  • Duda, R. O. und P. E. Hart. 1973. Pattern Classification and Scene Analysis. New York: John Wiley & Sons.

    Google Scholar 

  • Efron, B. und R. J. Tibshirani. 1993. An Introduction to the Bootstrap. New York: Chapman & Hall.

    Google Scholar 

  • Emele, M. C., M. Dorna, A. Lüdeling, H. Zinsmeister und C. Rohrer. 2000. Semantic-based Transfer. In: Wahlster ( 2000 ), 359–376.

    Google Scholar 

  • Epstein, M., K. Papineni, S. Roukos, T. Ward und S. A. Delia Pietra. 1996. Statistical Natural Language Understanding Using Hidden dumpings. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Atlanta, GA. Bd. 1. 176–179.

    Google Scholar 

  • Feynman, R. P., R. B. Leighton und M. Sands. 1963. The Feynman Lectures on Physics. Bd. 1. Reading, MA: Addison-Wesley.

    Google Scholar 

  • Gorin, A. L., G. Riccardi und J. H. Wright. 1997. How May I Help You? Speech Communication 23: 113–127.

    Article  Google Scholar 

  • Höge, H. und H. Ney. 1986. Architektur des sprachverstehenden Systems SPICOS. Kleinheubacher Berichte 29: 29–36.

    Google Scholar 

  • Jelinek, F. 1976. Speech Recognition by Statistical Methods. Proceedings of the IEEE 64: 532–556.

    Article  Google Scholar 

  • Macherey, K., F. J. Och und H. Ney. 2001. Natural Language Understanding Using Statistical Machine Translation. In: Proc. European Conf. on Speech Communication and Technology, Aalborg. 2205–2208.

    Google Scholar 

  • Nadas, A. 1985. Optimal Solution of a Training Problem in Speech Recognition. IEEE Trans, on Acoustics, Speech and Signal Processing 33: 326–329.

    Article  Google Scholar 

  • Ney, H., S. Nießen, F. J. Och, C. Tillmann, H. Sawaf und S. Vogel. 2000. Algorithms for Statistical Translation of Spoken Language. IEEE Trans, on Speech and Audio Processing 8(1): 24–36. Special Issue on Language Modeling and Dialogue Systems.

    Article  Google Scholar 

  • Ney, H. und S. Ortmanns. 2000. Progress in Dynamic Programming Search for LVCSR. Proceedings of the IEEE 88 (8): 1224–1240.

    Article  Google Scholar 

  • Ney, H., V. Öteinbiss, R. Haeb-Umbach, B.-H. Tran und U. Essen. 1994. An Overview of the Philips Research System for Large-Vocabulary Continuous-Speech Recognition. Int. Journal of Pattern Recognition and Artificial Intelligence 8 (1): 33–70.

    Article  Google Scholar 

  • Nießen, S., F. J. Och, G. Leusch und H. Ney. 2000. An Evaluation Tool for Machine Trans-lation: Fast Evaluation for MT Research. In: Proc. Int. Conf. on Language Resources and Evaluation (LREC-2000), Athen. 39–45.

    Google Scholar 

  • NIST02a. 2002. NIST (National Institute of Standards and Technology) evaluation conditions. URL http://www.nist.gov/speech/tests/mt/mt2001/resource/.

    Google Scholar 

  • NIST02b. 2002. NIST (=National Institute of Standards and Technology) scoring. URL http:// www.nist.gov/speech/tests/mt/doc/ngram-study.pdf.

    Google Scholar 

  • Och, F. J. und H. Ney. 2002. A Systematic Comparison of Various Alignment Models. Computational Linguistics (im Druck).

    Google Scholar 

  • Papineni, K., S. Roukos, T. Ward und W.-J. Zhu. 2001. BLEU: A Method for Automatic Evaluation of Machine Translation. Technischer Bericht. Yorktown Heights, NY: IBM.

    Google Scholar 

  • Pieraccini, R., E. Levin und E. Vidal. 1993. Learning How to Understand Language. In: Proc. European Conf. on Speech Communication and Technology, Berlin. 1407–1412.

    Google Scholar 

  • Rabiner, L. R. 1989. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE 77 (2): 257–286.

    Article  Google Scholar 

  • Reithinger, N. und R. Engel. 2000. Robust Content Extraction for Translation and Dialog Processing. In: Wahlster ( 2000 ), 428–437.

    Google Scholar 

  • Schürmann, J. 1994. Künstliche neuronale Netze als mathematische Strukturen. KI — Künstliche Intelligenz 20 (4): 48–52.

    Google Scholar 

  • Tessiore, L. und W. v. Hahn. 2000. Functional validation of a machine translation system: Verbmobil. In: Wahlster ( 2000 ), 611–631.

    Google Scholar 

  • Tillmann, C. und H. Ney. 2000. Word Re-ordering in a DP-based Approach to Statistical MT. In: Proc. Int. Conf. on Computational Linguistics (COLING-00), Saarbrücken. 850–856.

    Google Scholar 

  • Vogel, S., F. J. Och, C. Tillmann, S. Nieien, H. Sawaf und H. Ney. 2000. Statistical Methods for Machine Translation. In: Wahlster ( 2000 ), 377–393.

    Google Scholar 

  • Wahlster, W. (Hg.). 2000. Verbmobil: Foundations of Speech-to-Speech Translation. Berlin: Springer.

    Google Scholar 

  • Wang, Y.-Y. und A. Waibel. 1998. Modeling with Structures in Statistical Machine Translation. In: Proc. Annual Meeting of the Ass. for Computational Linguistics and Int. Conf. on Computational Linguistics (ACL-COLING-98), Montréal. 1357–1363.

    Google Scholar 

  • Wu, D. 1997. Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora. Computational Linguistics 23 (3): 377–403.

    Google Scholar 

  • Yamada, K. und K. Knight. 2001. A Syntax-based Statistical Translation Model. In: Proc. Annual Meeting of the Ass. for Computational Linguistics (ACL-98). 523–530.

    Google Scholar 

  • Young, S. J., J. J. Odell und P. C. Woodland. 1994. Tree-Based State Tying for High Accuracy Acoustic Modelling. In: Proc. ARPA Human Language Technology Workshop, Plainsboro, NJ. 286–291.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Aachen, Deutschland

    Hermann Ney

Authors
  1. Hermann Ney
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Münster, Deutschland

    Lea Cyrus , Hendrik Feddes , Frank Schumacher  & Petra Steiner , ,  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Deutscher Universitäts-Verlag GmbH, Wiesbaden,

About this chapter

Cite this chapter

Ney, H. (2003). Der statistische Ansatz in der maschinellen Sprachverarbeitung. In: Cyrus, L., Feddes, H., Schumacher, F., Steiner, P. (eds) Sprache zwischen Theorie und Technologie / Language between Theory and Technology. Sprachwissenschaft. Deutscher Universitätsverlag, Wiesbaden. https://doi.org/10.1007/978-3-322-81289-6_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-322-81289-6_17

  • Publisher Name: Deutscher Universitätsverlag, Wiesbaden

  • Print ISBN: 978-3-8244-4513-4

  • Online ISBN: 978-3-322-81289-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation