Modularized and Attention-Based Recurrent Convolutional Neural Network for Automatic Academic Paper Aspect Scoring

• Published in: Web Information Systems and Applications Vol. 11242; pp. 68 - 76
• Main Authors: Qiao, Feng, Xu, Lizhen, Han, Xiaowei
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2018; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Aspect scoring; Attention pooling; Convolutional neural network; Deep learning; LSTM
• ISBN: 3030029336; 9783030029333
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-02934-0_7

Thousands of academic papers are submitted at top venues each year. Manual audits are time-consuming and laborious. And the result may be influenced by human factors. This paper investigates a modularized and attention-based recurrent convolutional network model to represent academic paper and predict aspect scores. This model treats input text as module-document hierarchies, uses attention pooling CNN and LSTM to represent text, and outputs prediction with a linear layer. Empirical results on PeerRead data show that this model give the best performance among the baseline models.