TellMeWhy: Learning to Explain Corrective Feedback for Second Language Learners

Yi-Huei Lai, Jason Chang


Abstract
We present a writing prototype feedback system, TellMeWhy, to provide explanations of errors in submitted essays. In our approach, the sentence with corrections is analyzed to identify error types and problem words, aimed at customizing explanations based on the context of the error. The method involves learning the relation of errors and problem words, generating common feedback patterns, and extracting grammar patterns, collocations and example sentences. At run-time, a sentence with corrections is classified, and the problem word and template are identified to provide detailed explanations. Preliminary evaluation shows that the method has potential to improve existing commercial writing services.
Anthology ID:
D19-3040
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Sebastian Padó, Ruihong Huang
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
235–240
Language:
URL:
https://aclanthology.org/D19-3040
DOI:
10.18653/v1/D19-3040
Bibkey:
Cite (ACL):
Yi-Huei Lai and Jason Chang. 2019. TellMeWhy: Learning to Explain Corrective Feedback for Second Language Learners. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations, pages 235–240, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
TellMeWhy: Learning to Explain Corrective Feedback for Second Language Learners (Lai & Chang, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/D19-3040.pdf