Research on the Creation of Small-Scale English-Chinese Parallel Corpus for Manufacturing Systems

Abstract:

English, which is specially used in the field of manufacturing systems, belongs to ESP (English for specific purposes). In order to improve the effect of ESP education in China, it is very necessary to create an English-Chinese parallel corpus for aiding ESP teaching and learning. In this paper, a novel method is presented to create a small-scale English-Chinese parallel corpus by means of TMS (translation memory system). Firstly, the suitable English and Chinese texts are collected from network, publication and human translation; secondly, The English and Chinese texts are aligned and formatted by using the related TMS functions; then Chinese texts are split into words by using ICWSS (Intelligent Chinese Word Segmentation System); finally, the English-Chinese corpus is stored in cloud database. This small-scale English-Chinese parallel corpus can be searched through ParaConc and meet the basic needs of ESP teaching and learning. Since the method does not need to design new algorithm nor develop new software system, the construction of the corpus is much easier and more flexible compared to general large-scale corpus.

• Periodical: Applied Mechanics and Materials (Volume 421)
• Pages: 725-730
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.421.725
• Online since: September 2013
• Authors: Song Bin Bao
• Keywords: Computer-Assisted Language Learning, Parallel Corpus, Translation Memory System

References

[1] Anthony, E. M., Abdul Kadir, Z., A road not taken: a breakthrough in English for specific purposes via problem-based learning, Journal of Technical Education and Training, vol. 4, no. 1, pp.29-37, (2012).

[2] Sturkmen, H., One, I. C., Developing courses in English for specific purposes, The Electronic Journal for English as a Second Language, vol. 16, no. 1, pp.22-31, (2012).

[3] Spence, P., Liu, G. Z., Engineering English and the high-tech industry: A case study of English needs analysis of process integration engineers at a semiconductor manufacturing company in Taiwan. English for Specific Purposes, vol. 32, no. 2, pp.97-111, (2013).

DOI: 10.1016/j.esp.2012.11.003

[4] Sakamoto, M., Moving towards effective English language teaching in Japan: issues and challenges. Journal of Multilingual and Multicultural Development, vol. 33, no. 4, pp.409-420, (2012).

DOI: 10.1080/01434632.2012.661437

[5] LU, Y., Zhang, X., Zheng, D., Automatic English-Chinese Parallel Corpus Acquisition and Sentences Extraction. Journal of Computational Information Systems, vol. 9, no. 6, pp.2365-2372, (2013).

[6] Ma, Y., He, Y., Way, A., van Genabith, J., Consistent translation using discriminative learning-a translation memory-inspired approach. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp.1239-1248, (2011).

[7] Steinberger, R., Eisele, A., Klocek, S., Pilos, S., Schlüter, P., Dgt-tm: A freely available translation memory in 22 languages. In Proceedings of the 8th International Conference on Language Resources and Evaluation, pp.454-459, (2012).

[8] Wu, D., He, D., Exploring the further integration of machine translation in English-Chinese cross language information access, Program: electronic library and information systems, vol. 46, no. 4, pp.429-457, (2012).

DOI: 10.1108/00330331211276495