Abstract
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.- Anthology ID:
- P19-1488
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4943–4951
- Language:
- URL:
- https://aclanthology.org/P19-1488
- DOI:
- 10.18653/v1/P19-1488
- Cite (ACL):
- Alona Sydorova, Nina Poerner, and Benjamin Roth. 2019. Interpretable Question Answering on Knowledge Bases and Text. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4943–4951, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Interpretable Question Answering on Knowledge Bases and Text (Sydorova et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/P19-1488.pdf