Language modelling as a multi-task problem

January 28, 2021


In this paper, we propose to study language modelling as a multi-task problem, bringing together three strands of research: multi-task learning, linguistics, and interpretability. Based on hypotheses derived from linguistic theory, we investigate whether language models adhere to learning principles of multi-task learning during training. To showcase the idea, we analyse the generalisation behaviour of language models as they learn the linguistic concept of Negative Polarity Items (NPIs). Our experiments demonstrate that a multi-task setting naturally emerges within the objective of the more general task of language modelling. We argue that this insight is valuable for multi-task learning, linguistics and interpretability research and can lead to exciting new findings in all three domains.

Download the Paper


Written by

Dieuwke Hupkes

Elia Bruni

Jaap Jumelet

Lucas Weber



Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.