ABSTRACT
During the COVID-19 pandemic, Chinese Patent Medicine (CPM) was proved efficient in preventing virus propagation. However, the current instant translations provided by automatic translation engines on the Internet have been fraught with inaccurate information, which hindered the spread of CPM to overseas. By pointing out the problems in machine translation, this paper offers some solutions to improving the quality of instant translation of CPM instructions. The key improvement is the multiple specially trained models for specific translations, in which the CPM Model has been specially trained for CPM instruction translation. It is found that the translations by specially trained models are noticeably improved in accuracy, grammar and readability, and with the most resemblance to the human expert translation. The paper concludes that machine translators are mimics of human translators, when machine translators follow human experts more closely, especially in a specific translation field, they can make better performances than before.
- Papineni, K., Roukos, S., Ward, T., & Zhu, W. J. (2002, July). Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics (pp. 311-318).Google Scholar
- Eck, M., Vogel, S., & Waibel, A. (2004). Improving statistical machine translation in the medical domain using the Unified Medical Language System. In Coling 2004: Proceedings of the 20th international conference on Computational Linguistics (pp. 792-798).Google Scholar
- Yao, Z. J. (2007). The Development of a Special MT System for Translating TCM Classics. Chinese Translators Journal, 72-75+95.Google Scholar
- Dušek, (2014). Machine translation of medical texts in the khresmoi project. In Proceedings of the Ninth Workshop on Statistical Machine Translation (pp. 221-228).Google ScholarCross Ref
- Liu, H., Liang, Y., Wang, L., Feng, X., & Guan, R. (2020). BioNMT: A Biomedical neural machine translation system. International Journal of Computers Communication & Control, 15(6).Google Scholar
- Sun, Y. (2022). Analysis of Chinese Machine Translation Training Based on Deep Learning Technology. Computational Intelligence and Neuroscience.Google Scholar
- Zhang, L. (2023). Application of Trados software in the English translation of Chinese patent medicine instructions. China Pharmacy, 366-369+379.Google Scholar
Index Terms
- Innovations to Machine Translation of Chinese Patent Medicine Instructions
Recommendations
Research on Element Sub-sentence in Chinese-English Patent Machine Translation
IALP '11: Proceedings of the 2011 International Conference on Asian Language ProcessingThis paper presents an approach to translate element sub-sentences which widely exist in Chinese patent documents. Element sub-sentence is a kind of language chunk in a sentence in which one part of sub-sentence is the headword and others are ...
Language Modeling for Syntax-Based Machine Translation Using Tree Substitution Grammars: A Case Study on Chinese-English Translation
The poor grammatical output of Machine Translation (MT) systems appeals syntax-based approaches within language modeling. However, previous studies showed that syntax-based language modeling using (Context-Free) Treebank Grammars was not very helpful in ...
Large aligned treebanks for syntax-based machine translation
We present a collection of parallel treebanks that have been automatically aligned on both the terminal and the non-terminal constituent level for use in syntax-based machine translation. We describe how they were constructed and applied to a syntax- ...
Comments