Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling
This work addresses the need for interpretability in NLP models, though it appears incremental as it builds on existing techniques like occlusion and language modeling.
The authors tackled the problem of explaining predictions from natural language processing classifiers by proposing OLM, a novel method combining occlusion and language modeling, which they showed to be theoretically sound and experimentally unique compared to other methods.
Deep neural networks are powerful statistical learners. However, their predictions do not come with an explanation of their process. To analyze these models, explanation methods are being developed. We present a novel explanation method, called OLM, for natural language processing classifiers. This method combines occlusion and language modeling, which are techniques central to explainability and NLP, respectively. OLM gives explanations that are theoretically sound and easy to understand. We make several contributions to the theory of explanation methods. Axioms for explanation methods are an interesting theoretical concept to explore their basics and deduce methods. We introduce a new axiom, give its intuition and show it contradicts another existing axiom. Additionally, we point out theoretical difficulties of existing gradient-based and some occlusion-based explanation methods in natural language processing. We provide an extensive argument why evaluation of explanation methods is difficult. We compare OLM to other explanation methods and underline its uniqueness experimentally. Finally, we investigate corner cases of OLM and discuss its validity and possible improvements.