Teachers spend a great amount of time grading free text answer type questions. To encounter this challenge an auto-grader system is proposed. The thesis illustrates that the auto-grader can be approached with simple, recurrent, and Transformer-based neural networks. Hereby, the Transformer-based models has the best performance. It is further demonstrated that geometric representation of question-answer pairs is a worthwhile strategy for an auto-grader. Finally, it is indicated that while the auto-grader could potentially assist teachers in saving time with grading, it is not yet on a level to fully replace teachers for this task.
About the author
Robin Richner was working as a Machine Learning Engineer in the edtech industry exploring ways to help teachers in their daily life. He now moved on to the web3 industry.
Dieser Download kann aus rechtlichen Gründen nur mit Rechnungsadresse in A, B, BG, CY, CZ, D, DK, EW, E, FIN, F, GR, HR, H, IRL, I, LT, L, LR, M, NL, PL, P, R, S, SLO, SK ausgeliefert werden.
Es gelten unsere Allgemeinen Geschäftsbedingungen: www.buecher.de/agb
Impressum
www.buecher.de ist ein Internetauftritt der buecher.de internetstores GmbH
Geschäftsführung: Monica Sawhney | Roland Kölbl | Günter Hilger
Sitz der Gesellschaft: Batheyer Straße 115 - 117, 58099 Hagen
Postanschrift: Bürgermeister-Wegele-Str. 12, 86167 Augsburg
Amtsgericht Hagen HRB 13257
Steuernummer: 321/5800/1497
USt-IdNr: DE450055826