Existing example retrieval systems do not in- clude grammatically incorrect examples, or only present a few examples, if any. Even if a retrieval system has a wide coverage of in- correct examples along with the correct coun- terparts, learners need to know whether their query includes errors. Considering the usabil- ity of retrieving incorrect examples, our pro- posed method uses a large-scale corpus and presents correct expressions along with incor- rect expressions using a grammatical error de- tection system so that the learner does not need to be aware of how to search for examples. In- trinsic and extrinsic evaluations indicate that our method improves the accuracy of example sentence retrieval and the quality of a learner's writing.
CITATION STYLE
Arai, M., Kaneko, M., & Komachi, M. (2019). Grammatical-error-aware incorrect example retrieval system for learners of japanese as a second language. In ACL 2019 - Innovative Use of NLP for Building Educational Applications, BEA 2019 - Proceedings of the 14th Workshop (pp. 296–305). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w19-4431
Mendeley helps you to discover research relevant for your work.