The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection

10/03/2022

∙

by   Sondre Wold, et al.

∙

0

∙

share

This paper studies the problem of injecting factual knowledge into large pre-trained language models. We train adapter modules on parts of the ConceptNet knowledge graph using the masked language modeling objective and evaluate the success of the method by a series of probing experiments on the LAMA probe. Mean P@K curves for different configurations indicate that the technique is effective, increasing the performance on subsets of the LAMA probe for large values of k by adding as little as 2.1 original models.