Automatic Text Scoring Using Neural Networks
- Submitting institution
-
King's College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 142457496
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/p16-1068
- Title of conference / published proceedings
- Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- First page
- 715
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- Year of publication
- 2016
- URL
-
https://www.aclweb.org/anthology/P16-1068
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 20
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- First deep learning framework for automated writing assessment (AWA), including a novel component on adapting word embeddings to better model the task, achieving a new state-of-the-art on public data for the task. Work shaped the field of AWA, moving away from laborious feature engineering. In addition, we propose the first framework for visualising such models’ internal ‘marking criteria’. Cahill (NCME-2018) comments that this is an important step forward, while Murdoch & Szlam (ICLR-2017) comment on the generality of the approach. Resulted in invited presentations: AAAI2021 Symposium on AI for K-12 Education; NewDirections2019 BritishCouncil (Chair; panel discussion on technology in assessment).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -