A Sequence to Sequence Learning for Chinese Grammatical Error Correction

  • Hongkai Ren
  • Liner YangEmail author
  • Endong Xun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11109)


Grammatical Error Correction (GEC) is an important task in natural language processing. In this paper, we introduce our system on NLPCC 2018 Shared Task 2 Grammatical Error Correction. The task is to detect and correct grammatical errors that occurred in Chinese essays written by non-native speakers of Mandarin Chinese. Our system is mainly based on the convolutional sequence-to-sequence model. We regard GEC as a translation task from the language of “bad” Chinese to the language of “good” Chinese. We describe the building process of the model in details. On the test data of NLPCC 2018 Shared Task 2, our system achieves the best precision score, and the \(F_{0.5}\) score is 29.02. Our final results ranked third among the participants.


Grammatical Error Correction Convolutional Sequence to Sequence Model Neural machine translation 



This research project is supported by the funds of Beijing Advanced Innovation Center for Language Resources (No. TYR17001), the Key Project of National Social Science Foundation of China (No. 16AYY007), and the Fundamental Research Funds for the Central Universities in BLCU (No. 18YCX001). We also thank Huimeng Zhang, JingJing Miao and Jin Zhao for helping to modify the paper.


  1. 1.
    Chollampatt, S., Ng, H.T.: Connecting the dots: towards human-level grammatical error correction. In: BEA@EMNLP (2017)Google Scholar
  2. 2.
    Chollampatt, S., Ng, H.T.: A multilayer convolutional encoder-decoder neural network for grammatical error correction. CoRR abs/1801.08831 (2018)Google Scholar
  3. 3.
    Chorowski, J., Bahdanau, D., Cho, K., Bengio, Y.: End-to-end continuous speech recognition using attention-based recurrent NN: first results. CoRR abs/1412.1602 (2014)Google Scholar
  4. 4.
    Dahlmeier, D., Ng, H.T.: Better evaluation for grammatical error correction. In: NAACL (2012)Google Scholar
  5. 5.
    Dauphin, Y., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. In: ICML (2017)Google Scholar
  6. 6.
    Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.: Convolutional sequence to sequence learning. In: ICML (2017)Google Scholar
  7. 7.
    Ji, J., Wang, Q., Toutanova, K., Gong, Y., Truong, S., Gao, J.: A nested attention neural hybrid model for grammatical error correction. In: ACL (2017)Google Scholar
  8. 8.
    Junczys-Dowmunt, M., Grundkiewicz, R.: Phrase-based machine translation is state-of-the-art for automatic grammatical error correction. In: EMNLP (2016)Google Scholar
  9. 9.
    Junczys-Dowmunt, M., Grundkiewicz, R., Guha, S., Heafield, K.: Approaching neural grammatical error correction as a low-resource machine translation task. CoRR abs/1804.05940 (2018)Google Scholar
  10. 10.
    Yu, L.-C., Lee, L.H., Chang, L.P.: Overview of grammatical error diagnosis for learning Chinese as foreign language. In: NLP-TEA (2014)Google Scholar
  11. 11.
    Ling, W., Dyer, C., Black, A.W., Trancoso, I.: Two/too simple adaptations of word2vec for syntax problems. In: NAACL (2015)Google Scholar
  12. 12.
    Neubig, G.: Neural machine translation and sequence-to-sequence models: a tutorial. CoRR abs/1703.01619 (2017)Google Scholar
  13. 13.
    Ng, H.T., Wu, S.M., Wu, Y., Hadiwinoto, C., Tetreault, J.R.: The CoNLL-2013 shared task on grammatical error correction. In: CoNLL Shared Task (2013)Google Scholar
  14. 14.
    Rao, G., Zhang, B., Xun, E., Lee, L.H.: IJCNLP-2017 task 1: Chinese grammatical error diagnosis. In: IJCNLP (2017)Google Scholar
  15. 15.
    Rush, A.M., Chopra, S., Weston, J.: A neural attention model for abstractive sentence summarization. In: EMNLP (2015)Google Scholar
  16. 16.
    Schmaltz, A., Kim, Y., Rush, A.M., Shieber, S.M.: Adapting sequence models for sentence correction. In: EMNLP (2017)Google Scholar
  17. 17.
    Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. CoRR abs/1508.07909 (2016)Google Scholar
  18. 18.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15, 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Yuan, Z., Briscoe, T.: Grammatical error correction using neural machine translation. In: NAACL (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Beijing Advanced Innovation Center for Language ResourcesBeijingChina
  2. 2.School of Information ScienceBeijing Language and Culture UniversityBeijingChina

Personalised recommendations