This work presents a detailed comparison and analysis of the usage of cohesive devices by three Machine Translation systems from Chinese to English, in both SMT and NMT situations. By both a general analysis of sentence length as well as cohesive devices and detailed analysis of a sentence translation in SMT and NMT with human translation as a reference, it is shown that, compared with SMT, NMT system is better at handling cohesive ties such as additive, adverbs and pronouns; however, both SMT and NMT underperform at dealing with demonstratives and lexical cohesion. This suggests an evidence of improved translation quality and the necessity of pre-editing and post-editing cohesive devices in MT translations.
References
[1]
Bentivogli, L., Arianna, B., Mauro, C., & Marcello, F. (2016). Neural Versus Phrase-Based Machine Translation Quality: A Case Study. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, 1-5 November 2016, 257-267. https://doi.org/10.18653/v1/D16-1025
[2]
Denkowski, M., & Lavie, A. (2011). Meteor 1.3: Automatic Metric for Reliable Optimization and Evaluation of Machine Translation Systems. Proceedings of the EMNLP 2011 Workshop on Statistical Machine Translation, Edinburgh, 30-31 July 2011, 85-91.
[3]
Guo, F. Q. (2006). Critical Thinking and Translation Study on English-Chinese Textual Cohesive Ties. In D. F. Wang (Ed.), Functional Grammar and Translation Study (pp. 188-200). Guangzhou: Sun Yat-sen University Press.
[4]
Halliday, M. A. K., & Hasan, R. (1976). Cohesion in English. London: Longman.
[5]
Hoey, M. (1991/2000). Patterns of Lexis in Text. Oxford: Oxford University Press, Shanghai: Shanghai Foreign Language Education Press.
[6]
Hu, Z. L. (1994). Cohesion and Coherence of Text. Shanghai: Shanghai Foreign Language Education Press.
[7]
Niehues, J., Eunah, C., Thanh-Le, H., & Alex, W. (2016). Pre-Translation for Neural Machine Translation. Proceedings of the 26th International Conference on Computational Linguistics, Osaka, 11-17 December 2016, 1828-1836.
[8]
Papineni, K., Roukos, S., Ward, T., & Zhu, W. J. (2002). Bleu: A Method for Automatic Evaluation of Machine Translation. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Philadelphia, 6-12 July 2002, 311-318. https://doi.org/10.3115/1073083.1073135
[9]
Snover, M., Dorr, B., Schwartz, R., Micciulla, L., & Makhoul, J. (2006). A Study of Translation Edit Rate with Targeted Human Annotation. Proceedings of the 7th Conference of the Association for Machine Translation in the Americas, Cambridge, 8-12 August 2006, 223-231.
[10]
Toral, A., & Víctor, M. S. (2017). A Multifaceted Evaluation of Neural versus Statistical Machine Translation for 9 Language Directions. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, 3-7 April 2017, 1063-1073. https://doi.org/10.18653/v1/E17-1100
[11]
Wang, D. F. (2006). Comparison and Translation of English-Chinese Grammatical Cohesion. In D. F. Wang (Ed.), Functional Grammar and Translation Study (pp. 254-277). Guangzhou: Sun Yat-sen University Press.
[12]
Zhou, M. (2019). The Bright Future of ACL/NLP. https://www.microsoft.com/en-us/research/uploads/prod/2019/08/ACL-MingZh ou-50min-ming.v9.pdf
