Automatic scoring of short answers using justification cues estimated by BERT
Article Status
Published
Authors/contributors
- Takano, Shunya (Author)
- Ichikawa, Osamu (Author)
Title
Automatic scoring of short answers using justification cues estimated by BERT
Date
2022
Proceedings Title
Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
Conference Name
Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
Place
Seattle, Washington
Publisher
Association for Computational Linguistics
Pages
8-13
Language
en
Accessed
27/03/2023, 20:01
Library Catalogue
DOI.org (Crossref)
Extra
Citation Key: takano2022
<标题>: 使用 BERT 估计的理由提示进行简答自动评分
<AI Smry>: The proposed method reduces the training data from the 800 data required in the past to about 400 data, and still achieves scoring accuracy comparable to that of humans on the RIKEN dataset.
Citation
Takano, S., & Ichikawa, O. (2022). Automatic scoring of short answers using justification cues estimated by BERT. Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), 8–13. https://doi.org/10.18653/v1/2022.bea-1.2
Link to this record