A Neural Natural Language Processing System for Educational Resource Knowledge Domain Classification
Autor(en): | Schrumpf, J. Weber, F. Thelen, T. |
Herausgeber: | Kienle, A. Harrer, A. Haake, J.M. Lingnau, A. |
Stichwörter: | AI in Higher Education; Classification system; Contextual information; Dewey decimal classifications; Educational resource; Google+; High educations; Knowledge domains; Learning algorithms; Machine Learning; Machine learning, AI in high education; Machine-learning; Recommender Systems; State of the art, Natural language processing systems | Erscheinungsdatum: | 2021 | Herausgeber: | Gesellschaft fur Informatik (GI) | Journal: | Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI) | Volumen: | P-316 | Startseite: | 283 | Seitenende: | 288 | Zusammenfassung: | In higher education, educational resources are the vessel with which information get transferred to the learner. Information on the content discussed in the scope of the educational resources, however, is implicit and must be inferred by the user by reading the resource title or through contextual information. In this paper we present a state-of-the-art neural natural language processing system, based on Google-BERT, that maps educational resource titles into one of 905 classes from the Dewey Decimal Classification (DDC) system. We present model architecture, training procedure dataset properties and our performance analysis methodology. We show that aside from classification performance, our model implicitly learns the class hierarchy inherent to the DDC. © 2021 Gesellschaft fur Informatik (GI). All rights reserved. |
Beschreibung: | Conference of Die 19. Fachtagung Bildungstechnologien der Gesellschaft fur Informatik e.V., DELFI 2021 - 19th Conference on Educational Technologies of the German Informatics Society, DELFI 2021 ; Conference Date: 13 September 2021 Through 15 September 2021; Conference Code:177565 |
ISBN: | 9783885797104 | ISSN: | 1617-5468 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127381721&partnerID=40&md5=7d782350ae528d4ad9fcde90b4fab392 |
Show full item record