Intepreting & Improving Pretrained Language Models: A Probabilistic Conceptual Approach

Hengyi Wang, Zhiqing Hong, Desheng Zhang, Hao Wang

Keywords: Pretrained Lauguage Models, Generative Models, Probabilistic Graphical Models

TL;DR: We propose a hierarchical Bayesian deep learning model to provide concept-level interpretations of pretrained language models.

Abstract: Pretrained Language Models (PLMs) such as BERT and its variants have achieved remarkable success in natural language processing. To date, the interpretability of PLMs has primarily relied on the attention weights in their self-attention layers. However, these attention weights only provide word-level interpretations, failing to capture higher-level structures, and are therefore lacking in readability and intuitiveness. In this paper, we propose a hierarchical Bayesian deep learning model, dubbed continuous latent Dirichlet allocation (CLDA), to go beyond word-level interpretations and provide concept-level interpretations. Our CLDA is compatible with any attention-based PLMs and can work as either (1) an interpreter which interprets model predictions at the concept level without any performance sacrifice or (2) a regulator which is jointly trained with PLMs during finetuning to further improve performance. Experimental results on various benchmark datasets show that our approach can successfully provide conceptual interpretation and performance improvement for state-of-the-art PLMs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Probabilistic Methods (eg, variational inference, causal inference, Gaussian processes)