Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models

TL;DR

This paper introduces a formal framework and novel algorithms for hierarchical importance attribution in neural NLP models, improving explanation consistency, interpretability, and trust in models like LSTM and BERT.

Contribution

It proposes a formal method to quantify importance in hierarchical explanations and introduces SCD and SOC algorithms that outperform prior methods.

Findings

Algorithms outperform prior hierarchical explanation methods.

Enhanced visualization of semantic composition in models.

Improved human trust and interpretability of neural models.

Abstract

The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical explanation of neural network predictions. We identify non-additivity and context independent importance attributions within hierarchies as two desirable properties for highlighting word and phrase compositions. We show some prior efforts on hierarchical explanations, e.g. contextual decomposition, do not satisfy the desired properties mathematically, leading to inconsistent explanation quality in different models. In this paper, we start by proposing a formal and general way to quantify the importance of each word and phrase. Following the formulation, we propose Sampling and Contextual Decomposition (SCD) algorithm and Sampling and Occlusion (SOC) algorithm. Human and metrics evaluation on both LSTM models and BERT Transformer models on multiple datasets show that our algorithms outperform prior hierarchical explanation algorithms. Our algorithms help to visualize semantic composition captured by models, extract classification rules and improve human trust of models. Project page: https://inklab.usc.edu/hiexpl/