An Automated System for Correction of Rules of Transformation from Universal Networking Language into Natural Language

Authors

  • Aram A. Avetisyan Institute for Informatics and Automation Problems of NAS RA
  • Levon R. Hakobyan Institute for Informatics and Automation Problems of NAS RA

Keywords:

UNL, Machine translations, Transformation rules, Grammar

Abstract

An approach to automated correction of UNL grammar rules is implemented. The development process of the rule sets could be made in a more effective way if some tools are used which can find the rules responsible for possible errors and make suggestions about its correction. Several definitions for the formalization of the transformation process and the algorithm for such kind of functionality are created. The implementation of the algorithm in the UNDL Platform and some examples are described.

References

H. Uchida, M. Zhu, and T. Della Senta, A Gift for a Millennium, IAS/UNU, 1999.

R. Martins, UNL Wordnet, Mackenzie University, 2008.

UNDL Foundation web site, [Online]. Available: http://www.undlfoundation.org/

DeConverter Specification Version 2.6, UNL Center /UNDL Foundation 2002. UNL Center, Enconverter Specifications, Version 3.3 Tokyo, 2001.

Test Drive Corpus, UNDL Foundation, [Online]. Available: http://www.unlweb.net/wiki/EUGENE#Test_drive

Downloads

Published

2021-12-10

How to Cite

Avetisyan, A. A. ., & Hakobyan, L. R. . (2021). An Automated System for Correction of Rules of Transformation from Universal Networking Language into Natural Language. Mathematical Problems of Computer Science, 41, 114–121. Retrieved from http://mpcs.sci.am/index.php/mpcs/article/view/239

Issue

Vol. 41 (2014): Mathematical Problems of Computer Science

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.