Language Modelling as a Multi-Task Problem
Lucas Weber, Jaap Jumelet, Elia Bruni, Dieuwke Hupkes
Interpretability and Analysis of Models for NLP Long paper Paper
You can open the pre-recorded video in separate windows.
Abstract:
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.
NOTE: Video may display a random order of authors.
Correct author list is at the top of this page.