Automated Topical Component Extraction Using Neural Network Attention Scores from Source-based Essay Scoring

Haoran Zhang, Diane Litman


Abstract
While automated essay scoring (AES) can reliably grade essays at scale, automated writing evaluation (AWE) additionally provides formative feedback to guide essay revision. However, a neural AES typically does not provide useful feature representations for supporting AWE. This paper presents a method for linking AWE and neural AES, by extracting Topical Components (TCs) representing evidence from a source text using the intermediate output of attention layers. We evaluate performance using a feature-based AES requiring TCs. Results show that performance is comparable whether using automatically or manually constructed TCs for 1) representing essays as rubric-based features, 2) grading essays.
Anthology ID:
2020.acl-main.759
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8569–8584
Language:
URL:
https://aclanthology.org/2020.acl-main.759
DOI:
10.18653/v1/2020.acl-main.759
Bibkey:
Cite (ACL):
Haoran Zhang and Diane Litman. 2020. Automated Topical Component Extraction Using Neural Network Attention Scores from Source-based Essay Scoring. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8569–8584, Online. Association for Computational Linguistics.
Cite (Informal):
Automated Topical Component Extraction Using Neural Network Attention Scores from Source-based Essay Scoring (Zhang & Litman, ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2020.acl-main.759.pdf
Video:
 http://slideslive.com/38929052