Abstract
We describe a disambiguation method to handle different phenomena for target word selection in Machine Translation such as ambiguity, fixed expressions or collocations. CDM is a constraint-based approach exploiting language specific mapping patterns of source word readings to target words in order to limit analysis depth. It employs a gradual schema of modular layers in a specific order, incorporating a broad spectrum of sources, from linguistic over semantic up to domain, discourse and world knowledge. The model is applied to and partially implemented in LMT-GE, a machine translation system from German to English following the Logic-programming-based Machine Translation approach of McCord (1989).
Zusammenfassung
Der Beitrag beschreibt eine Disambiguierungsmethode für verschiedene Phänomene bei der Zielwortauswähl in der Maschinellen Ubersetzung, wie Ambiguität, fixierte Mehrwortausdrücke und Kollokationen. Wir verwenden einen constraintbasierten Ansatz, der sprachpaarspezifische Relationen zwischen ausgangssprachlichen Lesarten und zielsprachlichen Wörtern ausnutzt. In einer bestimmten Reihenfolge wird in einem modularen Stufenschema linguistisches, semantisches und bereichsspezifisches Wissen, Diskurs- und Weltwissen eingesetzt. Die Methode ist teilweise implementiert und wird in dem MÜ-Prototypen LMT-GE (Deutsch-Englisch) angewendet, der auf dem Ansatz von McCord (1989) zur MÜ nach Prinzipien der Logikprogrammierung basiert.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Alshawi, H. (1989). Analysing the dictionary definitions. In: Boguraev, B., T. Briscoe (eds.). Computational Lexicography for Natural Language Processing. 153–170. London:Longman.
Bläser, B., A. Storrer, U. Schwall (1992). A Reusable Lexical Databasefor Machine Translation. COLING 1992.
Breidt, E. (1991). Behandlung von mehrdeutigen Verben in der MÜ: Desambiguierung mit Unguistisch-ontologischen Informationen der Verbkomplemente. IWBS-Report 158, Scientific Centre IBM Germany, Heidelberg.
Brown, P. F. S. Della Pietra, A. Della Pietra, R. Mercer (1991). Word Sense Disambiguation using Statistical Methods. Proc. of the 29th Annual Meeting of the ACL, Berkeley, 264–270..
Brundage, J., M. Kresse, U. Schwall, A. Storrer (1992). Multiword Lexemes: Monolingual and Contrastive Typology for NLP and MT Systems. To appear as IWBS-Report, Scientific Centre IBM Germany, Heidelberg.
Dagan, I., A. Itai, U. Schwall (1991). Two Languages are more informative than One. Proc. of the 29th Annual Meeting of the ACL, Berkeley, 130–137.
Dahlgren, K. (1987). Using Commonsense Knowledge to Disambiguate Word Senses. In: Dahl, V., P. Saint-Dizier (eds). Natural Language Understanding and Logic Programming, Vol. 2. 255–276. Amsterdam: North-Holland.
Dahlgren, K., J. McDowell, E. P. Stabler (1989). Knowledge Representation for Commonsense Reasoning with Text. Computational Linguistics 15, No. 3, 149–170.
Everaert, M., E. van der Linden (eds.) (1989). Proceedings of the First Tilburg Workshop on Idioms, May 1989. Institute for Language Technology and Artifical Intelligence (ITK), Tilburg University, Holland.
Koller, W. (1979). Einführung in die Übersetzungswissenschaft. Heidelberg: UTB.
Leass, H., U. Schwall (1991). An Anaphora Resolution Procedure for Machine Translation. IWBS-Report 172, Scientific Centre IBM Germany, Heidelberg.
McCord, M. (1989). A New Version of the Machine Translation System LMT. Literary and Linguistic Computing, 4, 218–229.
McCord, M. (1992). The Slot Grammar System. In: Wedekind, J., Ch. Rohrer (eds.). Unification in Grammar. To appear in MIT Press.
Nirenburg, S. et al. (1989). KBMT-89, A Knowledge-based Machine Translation Project at the Centre for Machine Translation. Project Report. Carnegie Mellon University, Pittsburgh.
Rackow, U., I. Dagan, U. Schwall (1992). Automatic Translation of Noun Compounds.COLING 1992.
Rimon, M., M. McCord, U. Schwall, P. Martinez (1991). Advances in Machine Translation Research and Development in IBM. Proc. of the MT Summit III, Washington.
Velardi, P. (1991). Acquiring a semantic lexicon for Natural Language Processing. In: Zernik, U. (ed.). Lexical Acquisition. Exploiting On-Line Resources to Build a Lexicon. 341–368. Hillsdale, NJ: Lawrence Erlbaum Associates.
Veronis, J., N. Ide (1991). An Assessment of Semantic Information Automatically extracted from MRDs. Proc. of the 5th European Meeting of the ACL, Berlin, 227–232.
Zelinsky-Wibbelt, C. (1989). Machine Translation Based on Cognitive Linguistics: What Lexical Semantics Contributes to the Semantic Unity of a Sentence. Eurotra-D Working Paper No. 16. IAI, Saarbrücken.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Breidt, E., Schwall, U. (1992). A Combined Disambiguation Method for Target Word Selection. In: Görz, G. (eds) Konvens 92. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-77809-4_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-77809-4_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55959-7
Online ISBN: 978-3-642-77809-4
eBook Packages: Springer Book Archive