BiGBERT: Classifying Educational Web Resources for Kindergarten-12^th Grades

Authors

Garrett Allen, Boise State University
Brody Downs, Boise State University
Aprajita Shukla, Boise State University
Casey Kennington, Boise State UniversityFollow
Jerry Alan Fails, Boise State UniversityFollow
Katherine Landau Wright, Boise State UniversityFollow
Maria Soledad Pera, Boise State UniversityFollow

Document Type

Conference Proceeding

Publication Date

2021

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.

Comments

Advances in Information Retrieval is volume 12657 of the Lecture Notes in Computer Science book series.

Publication Information

Allen, Garrett; Downs, Brody; Shukla, Aprajita; Kennington, Casey; Fails, Jerry Alan; Wright, Katherine Landau; and Pera, Maria Soledad. (2021). "BiGBERT: Classifying Educational Web Resources for Kindergarten-12^th Grades". ECIR 2021: Advances in Information Retrieval, 176-184. https://doi.org/10.1007/978-3-030-72240-1_13