# Interpretable Question Answering on Knowledge Bases and Text

arXiv: https://arxiv.org/abs/1906.10924 · HTML: https://mlsanity.com/paper/1906.10924/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text](https://mlsanity.com/paper/2108.08614/) (2021)
- [Interpretation of Black Box NLP Models: A Survey](https://mlsanity.com/paper/2203.17081/) (2022)
- [Towards Explaining Subjective Ground of Individuals on Social Media](https://mlsanity.com/paper/2211.09953/) (2022)
- [How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?](https://mlsanity.com/paper/2310.18496/) (2023)
- [Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion](https://mlsanity.com/paper/2204.13097/) (2022)
- [Position: Intelligent Coding Systems Should Write Programs with Justifications](https://mlsanity.com/paper/2508.06017/) (2025)

## Abstract (arXiv)

Interpretability of machine learning (ML) models becomes more relevant with their increasing adoption. In this work, we address the interpretability of ML based question answering (QA) models on a combination of knowledge bases (KB) and text documents. We adapt post hoc explanation methods such as LIME and input perturbation (IP) and compare them with the self-explanatory attention mechanism of the model. For this purpose, we propose an automatic evaluation paradigm for explanation methods in the context of QA. We also conduct a study with human annotators to evaluate whether explanations help them identify better QA models. Our results suggest that IP provides better explanations than LIME or attention, according to both automatic and human evaluation. We obtain the same ranking of methods in both experiments, which supports the validity of our automatic evaluation paradigm.