# Comparing Feature Importance and Rule Extraction for Interpretability on Text Data

arXiv: https://arxiv.org/abs/2207.01420 · HTML: https://mlsanity.com/paper/2207.01420/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [On quantitative aspects of model interpretability](https://mlsanity.com/paper/2007.07584/) (2020)
- [An Analysis of LIME for Text Data](https://mlsanity.com/paper/2010.12487/) (2020)
- [A Sea of Words: An In-Depth Analysis of Anchors for Text Data](https://mlsanity.com/paper/2205.13789/) (2022)
- [A New Method to Compare the Interpretability of Rule-based Algorithms](https://mlsanity.com/paper/2004.01570/) (2020)

## Built on by (most cited first, 1 of 1)

- [Understanding Post-hoc Explainers: The Case of Anchors](https://mlsanity.com/paper/2303.08806/) (2023)

## Abstract (arXiv)

Complex machine learning algorithms are used more and more often in critical tasks involving text data, leading to the development of interpretability methods. Among local methods, two families have emerged: those computing importance scores for each feature and those extracting simple logical rules. In this paper we show that using different methods can lead to unexpectedly different explanations, even when applied to simple models for which we would expect qualitative coincidence. To quantify this effect, we propose a new approach to compare explanations produced by different methods.