A meta-learning augmented bidirectional transformer model for automatic short answer grading

Zichao Wang, Andrew S. Lan, Andrew E. Waters, Phillip Grimaldi, Richard G. Baraniuk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce ml-BERT, an effective machine learning method for automatic short answer grading when training data, i.e., graded answers, is limited. Our method combines BERT (Bidirectional Representation of the Transformer), the state-of-the-art model for learning textual data representations, with meta-learning, a training framework that leverages additional data and learning tasks to improve model performance when labeled data is limited. Our intuition is to use meta-learning to help us learn an initialization of the BERT parameters in a specific target subject domain using un-labeled data, thus fully leveraging the limited labeled training data for the grading task. Experiments on a real-world student answer dataset demonstrate the promise of ml-BERT method for automatic short answer grading.

Original languageEnglish (US)
Title of host publicationEDM 2019 - Proceedings of the 12th International Conference on Educational Data Mining
EditorsCollin F. Lynch, Agathe Merceron, Michel Desmarais, Roger Nkambou
PublisherInternational Educational Data Mining Society
Pages667-670
Number of pages4
ISBN (Electronic)9781733673600
StatePublished - 2019
Event12th International Conference on Educational Data Mining, EDM 2019 - Montreal, Canada
Duration: Jul 2 2019Jul 5 2019

Publication series

NameEDM 2019 - Proceedings of the 12th International Conference on Educational Data Mining

Other

Other12th International Conference on Educational Data Mining, EDM 2019
CountryCanada
CityMontreal
Period7/2/197/5/19

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications

Fingerprint Dive into the research topics of 'A meta-learning augmented bidirectional transformer model for automatic short answer grading'. Together they form a unique fingerprint.

Cite this