A Grammatical Analysis on Machine Translation Errors

  • Shili Ge
  • Susu Wu
  • Xiaoxiao Chen
  • Rou Song
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 954)


Machine translation errors are classified into groups of three grammatical levels: clause errors, clause-complex errors and textual errors, with a purpose to unravel causes leading to these errors. As illustrated with examples, clause complex presents different grammatical features from clause and the structural differences between Chinese and English at clause-complex level are the fundamental source of machine translation errors. This research, from perspectives of translation from Chinese to English and translation from English to Chinese, categorized clause-complex level structural differences between English and Chinese. The effects of these differences on machine translation are also analyzed, while future improvement suggestions on machine translation technology are provided accordingly.


Error analysis Machine translation Clause complex Naming-telling structure 



This research is sponsored by the grant of National Natural Science Foundation No. 61672175, the 2016 Key Project of the National Languages Committee (ZDI135-30), and the Science and Technology Development Project of Guangdong Province, China (2017A020220002).


  1. 1.
    Zhao, Y.: A Grammar of Spoken Chinese. Translated by Lv, S. The Commercial Press, Beijing (1979)Google Scholar
  2. 2.
    Zhu, D.: The Lecture Notes of Grammar. The Commercial Press, Beijing (1982)Google Scholar
  3. 3.
    Shen, J.: On minor sentences and flowing sentences in Chinese: In commemoration of the 120th birthday of Yuen Ren Chao. Stud. Chin. Lang. 5, 403–415 (2012)Google Scholar
  4. 4.
    Song, R.: Clause complex and naming-telling structure in Chinese. In: Jie, C., Liu, M. (eds.) Frontiers of Empirical and Corpus Linguistics. China Social Sciences Press, Beijing (in press)Google Scholar
  5. 5.
    Ge, S., Song, R.: The naming sharing structure and its cognitive meaning in Chinese and English. In: Xiong, D., Duh, K., Agirre, E., Aranberri, N., Wang, H. (eds.) Proceedings of the 2nd Workshop on Semantics-Driven Machine Translation (SedMT 2016), pp. 13–21. Association for Computational Linguistics (ACL), Stroudsburg (2016)Google Scholar
  6. 6.
    Qin, Y.: An analytical study of neural network machine translation and its impacts on translation teaching. Technol. Enhanc. Foreign Lang. Educ. 4, 51–56 (2018)Google Scholar
  7. 7.
    Wu, H., Zhang, H., Li, J., Zhu, J., Yang, M., Li, S.: Training machine translation quality estimation model based on pseudo data. Acta Sci. Nat. Univ. Pekin. 54(2), 279–285 (2018)zbMATHGoogle Scholar
  8. 8.
    Halliday, M.A.K., Matthiessen, C.: An Introduction to Functional Grammar, 3rd edn. Hodder Arnold, London (2004)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Guangdong University of Foreign StudiesGuangzhouChina

Personalised recommendations