Co-Attention Based Neural Network for Source-Dependent Essay Scoring
TL
TL;DR
It is shown that the co-attention based neural network model provides reliable score prediction of source-dependent responses and the attention of the model is similar to the expert opinions with examples.
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.
References27 items
1
Attention-based Recurrent Convolutional Neural Network for Automatic Essay Scoring
2
Word Embedding for Response-To-Text Assessment of Evidence
3
Assessing Students’ Use of Evidence and Organization in Response-to-Text Writing: Using Natural Language Processing for Rubric-Based Automated Scoring
4
Bidirectional Attention Flow for Machine Comprehension
5