XplaiNLI: Explainable Natural Language Inference through Visual Analytics
Aikaterini-Lida Kalouli, Rita Sevastjanova, Valeria de Paiva, Richard Crouch, Mennatallah El-Assady
Abstract
Advances in Natural Language Inference (NLI) have helped us understand what state-of-the-art models really learn and what their generalization power is. Recent research has revealed some heuristics and biases of these models. However, to date, there is no systematic effort to capitalize on those insights through a system that uses these to explain the NLI decisions. To this end, we propose XplaiNLI, an eXplainable, interactive, visualization interface that computes NLI with different methods and provides explanations for the decisions made by the different approaches.- Anthology ID:
- 2020.coling-demos.9
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Michal Ptaszynski, Bartosz Ziolko
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics (ICCL)
- Note:
- Pages:
- 48–52
- Language:
- URL:
- https://aclanthology.org/2020.coling-demos.9
- DOI:
- 10.18653/v1/2020.coling-demos.9
- Cite (ACL):
- Aikaterini-Lida Kalouli, Rita Sevastjanova, Valeria de Paiva, Richard Crouch, and Mennatallah El-Assady. 2020. XplaiNLI: Explainable Natural Language Inference through Visual Analytics. In Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations, pages 48–52, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL).
- Cite (Informal):
- XplaiNLI: Explainable Natural Language Inference through Visual Analytics (Kalouli et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2020.coling-demos.9.pdf