Paper ID: 2210.00907

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

Sondre Wold

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% additional parameters to the original models.

Submitted: Oct 3, 2022