Co-Attention Based Neural Network for Source-Dependent Essay Scoring

Haoran Zhang, Diane Litman


Abstract
This paper presents an investigation of using a co-attention based neural network for source-dependent essay scoring. We use a co-attention mechanism to help the model learn the importance of each part of the essay more accurately. Also, this paper shows that the co-attention based neural network model provides reliable score prediction of source-dependent responses. We evaluate our model on two source-dependent response corpora. Results show that our model outperforms the baseline on both corpora. We also show that the attention of the model is similar to the expert opinions with examples.
Anthology ID:
W18-0549
Original:
W18-0549v1
Version 2:
W18-0549v2
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:
399–409
Language:
URL:
https://aclanthology.org/W18-0549
DOI:
10.18653/v1/W18-0549
Bibkey:
Cite (ACL):
Haoran Zhang and Diane Litman. 2018. Co-Attention Based Neural Network for Source-Dependent Essay Scoring. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 399–409, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Co-Attention Based Neural Network for Source-Dependent Essay Scoring (Zhang & Litman, BEA 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-0549.pdf