我們提出一種學習語言的方法，著重在提升寫作的文法能力的等級。在我們的研究路線中，我們分析使用者輸入的句子以得到其文法結構，以期收集統計文法元素與例子。此方法涉及分辨句子字詞與標點符號、剖析句子並辨識其文法元素與等級。在執行時，對學習者輸入的句子進行分析，再根據文法元素之間的關聯，推薦進階的文法元素，並從事前辨識好的大量範例中，提示最有可能的文法元素與範例。我們提出了一個雛形的分析及建議系統 Level-Up。此系統將此方法應用於大規模語料庫，以及學習者的句子或文章中，以協助學習者進行寫作或閱讀。根據我們對建議模型的初步評估，此方法對學習者有潛力提供有效的輔助，並提供一個和現在文法改錯系統不同的方向。

We introduce a method for learning to generate suggestions on a given sentence or essay for improving the proficiency level. In our approach, essays are transformed into a sequence of grammatical elements aimed at providing suggestions for using more advanced grammatical elements related to the elements identified. The method involves parsing the essays, identifying grammatical elements and extracting grammatical elements from datasets. At run-time, essays are transformed into a set of grammatical elements, and re-ranking is performed on the extracted elements to recommend higher-level grammatical elements. We present a prototype coaching system, Level-Up, that applies the method to British National Corpus in order to assist learners in writing and reading. Preliminary evaluation on a set of representative sentences shows that the method has potential in assisting writing in a way different from existing commercial writing services.

Abstract ................... i
摘要 ................... ii
致謝 ................... iii
Contents ................... iv
List of Figures ................... vi
List of Tables ................... vii
1 Introduction ................... 1
2 Related Work ................... 7
3 Methodology ................... 11
4 Experiment and Evaluation ................... 21
5 Future Work and Conclusion ................... 27
Appendices ................... 29
Reference ................... 31

1. Øistein E. Andersen, Helen Yannakoudakis, Fiona Barker, and Tim Parish. Devel- oping and testing a self-assessment and tutoring system. In BEA@NAACL-HLT, 2013a.
2. Øistein E. Andersen, Helen Yannakoudakis, Fiona Barker, and Tim Parish. De- veloping and testing a self-assessment and tutoring system. In Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Ap- plications, pages 32–41. Association for Computational Linguistics, 2013b. URL http://aclweb.org/anthology/W13-1704.
3. Yigal Attali and Jill Burstein. Automated essay scoring with e-rater v.2.0. Journal of Technology, Learning, and Assessment, 2006.
4. Inge Bartning, M Martin, and Ineke Vedder. Communicative proficiency and linguistic development: intersections between sla and language testing research. 04 2019.
5. Christopher Bryant and Ted Briscoe. Language model based grammatical error correction without annotated training data. In BEA@NAACL-HLT, 2018.
6. Steven Burrows, Iryna Gurevych, and Benno Stein. The eras and trends of automatic short answer grading. International Journal of Artificial Intelligence in Education, 25(1):60–117, Mar 2015. ISSN 1560-4306. doi: 10.1007/ s40593-014-0026-8. URL https://doi.org/10.1007/s40593-014-0026-8.
7. Hongbo Chen and Ben He. Automated essay scoring by maximizing human- machine agreement. In Proceedings of the 2013 Conference on Empirical Meth- ods in Natural Language Processing, pages 1741–1752. Association for Compu- tational Linguistics, 2013. URL http://aclweb.org/anthology/D13-1180.
8. Collins Cobuild et al. Collins Cobuild English Grammar. Collins Cobuild, 2005.
British National Corpus. 2001. URL http://www.natcorp.ox.ac.uk.
9. Council of Europe. Common European Framework of Reference for Languages: Learning, Teaching, Assessment. Common European Framework of Reference for Languages: Learning, Teaching, Assessment. Cambridge University Press, 2001. ISBN 9780521005319. URL https://books.google.com.tw/books?id= PygQ8Gk4k4YC.
10. Fei Dong, Yue Zhang, and Jie Yang. Attention-based recurrent convolutional neu- ral network for automatic essay scoring. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 153–162. Association for Computational Linguistics, 2017. doi: 10.18653/v1/K17-1017. URL http://aclweb.org/anthology/K17-1017.
11. Na-Rae Han, Martin Chodorow, and Claudia Leacock. Detecting errors in english article usage by non-native speakers. Nat. Lang. Eng., 12(2):115–129, June 2006. ISSN 1351-3249. doi: 10.1017/S1351324906004190. URL http://dx.doi.org/ 10.1017/S1351324906004190.
12. Julia Hancke and Detmar Meurers. Exploring cefr classification for german based on rich linguistic modeling. pages 54–56, 01 2013.
13. Marti A. Hearst. Can natural language processing become natural language coach- ing? In ACL, 2015.
14. Matthew Honnibal and Ines Montani. spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. To appear, 2017.
15. Adam Kilgarriff, Milos Husa ́k, Katy McAdam, Michael Rundell, and Pavel Rychly`. Gdex: Automatically finding good dictionary examples in a corpus. In Proc. Euralex, 2008.
16. Ekaterina Kochmar and Ted Briscoe. Detecting learner errors in the choice of content words using compositional distributional semantics. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguis- tics: Technical Papers, pages 1740–1751. Dublin City University and Association for Computational Linguistics, 2014. URL http://aclweb.org/anthology/ C14-1164.
17. John Lee and Stephanie Seneff. Correcting misuse of verb forms. In Proceedings of ACL-08: HLT, pages 174–182. Association for Computational Linguistics, 2008. URL http://aclweb.org/anthology/P08-1021.
18. Robert Lew, Ana Frankenberg-Garcia, Geraint Paul Rees, Jonathan C Roberts, and Nirwan Sharma. Collocaid: A real-time tool to help academic writers with english collocations. In The XVIII EURALEX International Congress, page 165, 2018.
19. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. Dis- tributed representations of words and phrases and their compositionality. In Proceedings of the 26th International Conference on Neural Information Pro- cessing Systems - Volume 2, NIPS’13, pages 3111–3119, USA, 2013. Curran As- sociates Inc. URL http://dl.acm.org/citation.cfm?id=2999792.2999959.
20. Ildiko ́ Pil ́an, Elena Volodina, and Torsten Zesch. Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert- written coursebooks. In COLING, 2016.
21. Radim Rˇeh ̊uˇrek and Petr Sojka. Software Framework for Topic Modelling with Large Corpora. In Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, pages 45–50, Valletta, Malta, May 2010. ELRA. http: //is.muni.cz/publication/884893/en.
22. Marek Rei and Anders Søgaard. Jointly learning to label sentences and tokens. CoRR, abs/1811.05949, 2018.
23. Marek Rei and Helen Yannakoudakis. Compositional sequence labeling models for error detection in learner writing. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1181–1191. Association for Computational Linguistics, 2016. doi: 10.18653/v1/ P16-1112. URL http://aclweb.org/anthology/P16-1112.
24. Marek Rei and Helen Yannakoudakis. Auxiliary objectives for neural error detection models. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pages 33–43. Association for Computational Linguistics, 2017. doi: 10.18653/v1/W17-5004. URL http: //aclweb.org/anthology/W17-5004.
25. Marek Rei, Mariano Felice, Zheng Yuan, and Ted Briscoe. Artificial error gen- eration with machine translation and syntactic patterns. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applica- tions, pages 287–292. Association for Computational Linguistics, 2017. doi: 10.18653/v1/W17-5032. URL http://aclweb.org/anthology/W17-5032.
26. Mark David Shermis and Jill Burstein. Handbook of automated essay evaluation : current applications and new directions. 2013.
27. J. Sinclair. Collins Cobuild English grammar. Collins Cobuild. HarperCollins, 2005. ISBN 9780007183876. URL https://books.google.com.tw/books?id= Kcl4AAAAIAAJ.
28. Ana ̈ıs Tack, Thomas Fran ̧cois, Sophie Roekhaut, and C ́edrick Fairon. Human and automated cefr-based grading of short answers. In BEA@EMNLP, 2017.
29. Kaveh Taghipour and Hwee Tou Ng. A neural approach to automated essay scor- ing. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1882–1891. Association for Computational Linguis- tics, 2016. doi: 10.18653/v1/D16-1193. URL http://aclweb.org/anthology/ D16-1193.
30. Joel Tetreault, Jill Burstein, Ekaterina Kochmar, Claudia Leacock, and Helen Yannakoudakis. Proceedings of the thirteenth workshop on innovative use of nlp for building educational applications. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications. Association for Computational Linguistics, 2018. URL http://aclweb.org/anthology/ W18-0500.
31. Sowmya Vajjala. Automatic cefr level prediction for estonian learner text. 2014.
32. Sowmya Vajjala. Automated assessment of non-native learner essays: Investigat- ing the role of linguistic features. International Journal of Artificial Intelligence in Education, 28:79–105, 2017.
33. Helen Yannakoudakis, Øistein E. Andersen, Ardeshir Geranpayeh, Ted Briscoe, and Diane Nicholls. Developing an automated writing placement system for esl learners. 2018.
34. Tzu-Hsi Yen, Jian-Cheng Wu, Jim Chang, Joanne Boisson, and Jason Chang. Writeahead: Mining grammar patterns in corpora for assisted writing. Proceed- ings of ACL-IJCNLP 2015 System Demonstrations, pages 139–144, 2015.