Log In Sign Up

Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling

by   David Harbecke, et al.

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.


page 1

page 2

page 3

page 4


Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling

Recently, state-of-the-art NLP models gained an increasing syntactic and...

On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation

In the recent advances of natural language processing, the scale of the ...

Local Interpretations for Explainable Natural Language Processing: A Survey

As the use of deep learning techniques has grown across various fields o...

GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language

Helping end users comprehend the abstract distribution shifts can greatl...

WT5?! Training Text-to-Text Models to Explain their Predictions

Neural networks have recently achieved human-level performance on variou...

Fairwashing Explanations with Off-Manifold Detergent

Explanation methods promise to make black-box classifiers more transpare...

On Guaranteed Optimal Robust Explanations for NLP Models

We build on abduction-based explanations for ma-chine learning and devel...