Abstract
This paper describes our use of two recurrent neural network sequence models: sequence labelling and sequence-to-sequence models, for the prediction of future learner errors in our submission to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM). We show that these two models capture complementary information as combining them improves performance. Furthermore, the same network architecture and group of features can be used directly to build competitive prediction models in all three language tracks, demonstrating that our approach generalises well across languages.- Anthology ID:
- W18-0547
- Volume:
- Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Joel Tetreault, Jill Burstein, Ekaterina Kochmar, Claudia Leacock, Helen Yannakoudakis
- Venue:
- BEA
- SIG:
- SIGEDU
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 381–388
- Language:
- URL:
- https://aclanthology.org/W18-0547
- DOI:
- 10.18653/v1/W18-0547
- Cite (ACL):
- Zheng Yuan. 2018. Neural sequence modelling for learner error prediction. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 381–388, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Neural sequence modelling for learner error prediction (Yuan, BEA 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/W18-0547.pdf