Raqamli Transformatsiya va Sun’iy Intellekt
A HYBRID RULE-BASED AND TRANSFORMER APPROACH FOR UZBEK-ENGLISH MACHINE TRANSLATION: EVALUATION USING METEOR
1 Professor of Tashkent University of Information Technologies named after Mukhammad Al-Khwrazmi
2 Senior lecturer of the Pharmaceutical Education and Research Institute
3 PhD of the the Department of Multimedia
Zenodo DOI: 10.5281/zenodo.19695585
Abstract
This article presents how hybrid translation tool works. Specifically, it indicates rule-based translation’s IDF0 and also gives information about our tranlation system dataset which is done based transformer model. Moreover, it adduces the output evaluation of machine translation quality using the METEOR metric, with comparing the output of the English-Uzbek translation tool against human-produced translations. The study discusses how evaluation methodologies for machine translation systems work in bilingual contexts, emphasizing the importance across diverse domains. With the rapid enhancement of technology, there are different translation tools, each improving translation precision and fluency. This research provides a detailed analysis of translation evaluation metrics, specifically METEOR, applied to sentence-level translation tasks from English to Uzbek. It shows how low-resourced language is translated in our translation and how it is close to human translation.
References
- White, J., O'Connell, T. and O'Mara, F. (1994) "The ARPA MT Evaluation Methodologies: Evolution, Lessons, and Future Approaches". Proceedings of the 1st Conference of the Association for Machine Translation in the Americas. Columbia, MD pp. 193–20.
- Papineni, K., Roukos, S., Ward, T., and Zhu, W. J. (2002). "BLEU: a method for automatic evaluation of machine translation" in ACL-2002: 40th Annual meeting of the Association for Computational Linguistics pp. 311–318
- ALPAC (1966) "Languages and machines: computers in translation and linguistics". A report by the Automatic Language Processing Advisory Committee, Division of Behavioral Sciences, National Academy of Sciences, National Research Council. Washington, D.C.: National Academy of Sciences, National Research Council, 1966.
- S. Banerjee, and A. Lavie, “METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments,” In Proceedings of Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and/or Summarization at the 43rd Annual Meeting of the Association of Computational Linguistics (ACL-2005), Ann Arbor, Michigan, pp. 65-72, 2005.
- Banerjee, S. and Lavie, A. (2005) "METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments" in Proceedings of Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and/or Summarization at the 43rd Annual Meeting of the Association of Computational Linguistics (ACL-2005), Ann Arbor, Michigan, June 2005.
- N. Peng, L. Liu, Y. Wang, L. Wang, Y. Wei, and Y. Wang, “Quality Evaluation Model of Automatic Machine Translation Based on Deep Learning Algorithm,” in Proc. 2023 4th Int. Conf. for Emerging Technology (INCET), Belgaum, India, May 26–28, 2023.
- S. Banerjee and A. Lavie, "METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments," in Proc. ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, Ann Arbor, MI, USA, June 2005, pp. 65–72.
- M. Labied, A. Belangour, and M. Banane, “Assessing Speech-to-Text Translation Quality: An Overview of Key Metrics,” in Proc. 2024 Int. Conf. on Decision Aid Sciences and Applications (DASA), 2024, doi: 10.1109/DASA63652.2024.10836447.