Advertisement

Combined Technology of Lexical Selection in Rule-Based Machine Translation

  • Ualsher Tukeyev
  • Dina Amirova
  • Aidana Karibayeva
  • Aida Sundetova
  • Balzhan Abduali
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10449)

Abstract

This paper describes process of solving the task of lexical selection for English-Kazakh (and vice versa) machine translation system based on combined technology. Proposed combined technology is including the constraint grammar model and maximum entropy model for more effective solution of the problem of lexical selection for English-Kazakh (and vice-versa) language pair. Results are presented by comparing two technologies separately and together in Apertium English-Kazakh (and vice versa) system.

Keywords

Lexical selection Combined technology Machine translation Source language Target language Sense Ambiguity 

References

  1. 1.
    Tyers, F.M., Sánchez-Martınez, F., Forcada, M.L.: Unsupervised training of maximum-entropy models for lexical selection in rule-based machine translation. In: Proceedings of the 18th Annual Conference of the European Association for Machine Translation (EAMT 2015). Antalya, Turkey, pp. 145–153 (2015)Google Scholar
  2. 2.
    Berger, A., Pietra, S.D., Pietra, V.D.: A maximum entropy approach to natural language processing. Comput. Linguist. 22(1), 39–71 (1996)Google Scholar
  3. 3.
    Mareček, D., Popel, M., Z Žabokrtský, Z.: Maximum entropy translation model in dependency-based MT framework. In: Proceedings of the Joint 5th Workshop on Statistical Machine Translation and MetricsMATR, pp. 201–206, Uppsala, Sweden, 15–16 July 2010Google Scholar
  4. 4.
    Tyers, F.M.: Feasible lexical selection for rule-based machine translation. Ph.D. thesis – Universitat d’Alicante, May 2013, 110 p.Google Scholar
  5. 5.
  6. 6.
    Della Pietra, S., Della Pietra, V., Lafferty, J.: Inducing features of random fields. IEEE Trans. Pattern Anal. Mach. Intell. 19(4), 1–13 (1997)CrossRefGoogle Scholar
  7. 7.
  8. 8.
    Public services and information online. www.egov.kz

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Ualsher Tukeyev
    • 1
  • Dina Amirova
    • 1
  • Aidana Karibayeva
    • 1
  • Aida Sundetova
    • 1
  • Balzhan Abduali
    • 1
  1. 1.Information Systems DepartmentAl-Farabi Kazakh National UniversityAlmatyKazakhstan

Personalised recommendations