BiGBERT

Classifying Educational Web Resources for Kindergarten-12th Grades

Conference Paper (2021)
Author(s)

Garrett Allen (Boise State University)

Brody Downs (Boise State University)

Aprajita Shukla (Boise State University)

Casey Kennington (Boise State University)

Jerry Alan Fails (Boise State University)

Katherine Landau Wright (Boise State University)

Maria Soledad Pera (Boise State University)

DOI related publication
https://doi.org/10.1007/978-3-030-72240-1_13 Final published version
More Info
expand_more
Publication Year
2021
Language
English
Pages (from-to)
176-184
Publisher
Springer
ISBN (print)
9783030722395
Event
Downloads counter
207

Abstract

In this paper, we present BiGBERT, a deep learning model that simultaneously examines URLs and snippets from web resources to determine their alignment with children’s educational standards. Preliminary results inferred from ablation studies and comparison with baselines and state-of-the-art counterparts, reveal that leveraging domain knowledge to learn domain-aligned contextual nuances from limited input data leads to improved identification of educational web resources.