PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure

TL;DR

PEACH introduces a tree-based explanation method for NLP models that uses pretrained embeddings to provide human-interpretable insights into text classification decisions, aiding model understanding and debugging.

Contribution

It presents a novel tree-based explanation technique compatible with any pretrained contextual embeddings, enhancing interpretability and analysis of NLP classifiers.

Findings

PEACH effectively visualizes feature importance and model decisions.

It outperforms or matches existing pretrained model explanations.

The method aids in dataset debugging and understanding model errors.

Abstract

In this work, we propose a novel tree-based explanation technique, PEACH (Pretrained-embedding Explanation Across Contextual and Hierarchical Structure), that can explain how text-based documents are classified by using any pretrained contextual embeddings in a tree-based human-interpretable manner. Note that PEACH can adopt any contextual embeddings of the PLMs as a training input for the decision tree. Using the proposed PEACH, we perform a comprehensive analysis of several contextual embeddings on nine different NLP text classification benchmarks. This analysis demonstrates the flexibility of the model by applying several PLM contextual embeddings, its attribute selections, scaling, and clustering methods. Furthermore, we show the utility of explanations by visualising the feature selection and important trend of text classification via human-interpretable word-cloud-based trees, which clearly identify model mistakes and assist in dataset debugging. Besides interpretability, PEACH outperforms or is similar to those from pretrained models.