Abstract
The opaque nature of many machine learning techniques prevents the wide adoption of powerful information processing tools for high stakes scenarios. The emerging field eXplainable Artificial Intelligence (XAI) aims at providing justifications for automatic decision-making systems in order to ensure reliability and trustworthiness in the users. For achieving this vision, we emphasize the importance of a natural language textual modality as a key component for a future intelligent interactive agent. We outline the challenges of XAI and review a set of publications that work in this direction.- Anthology ID:
- 2020.nl4xai-1.6
- Volume:
- 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence
- Month:
- November
- Year:
- 2020
- Address:
- Dublin, Ireland
- Editors:
- Jose M. Alonso, Alejandro Catala
- Venue:
- NL4XAI
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 22–27
- Language:
- URL:
- https://aclanthology.org/2020.nl4xai-1.6
- DOI:
- Cite (ACL):
- Ettore Mariotti, Jose M. Alonso, and Albert Gatt. 2020. Towards Harnessing Natural Language Generation to Explain Black-box Models. In 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, pages 22–27, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Towards Harnessing Natural Language Generation to Explain Black-box Models (Mariotti et al., NL4XAI 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.nl4xai-1.6.pdf