Content Selection for Explanation Requests in Customer-Care Domain

Luca Anselma, Mirko Di Lascio, Dario Mana, Alessandro Mazzei, Manuela Sanguinetti


Abstract
This paper describes a content selection module for the generation of explanations in a dialogue system designed for customer care domain. First we describe the construction of a corpus of a dialogues containing explanation requests from customers to a virtual agent of a telco, and second we study and formalize the importance of a specific information content for the generated message. In particular, we adapt the notions of importance and relevance in the case of schematic knowledge bases.
Anthology ID:
2020.nl4xai-1.3
Volume:
2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence
Month:
November
Year:
2020
Address:
Dublin, Ireland
Venue:
NL4XAI
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
5–10
Language:
URL:
https://aclanthology.org/2020.nl4xai-1.3
DOI:
Bibkey:
Cite (ACL):
Luca Anselma, Mirko Di Lascio, Dario Mana, Alessandro Mazzei, and Manuela Sanguinetti. 2020. Content Selection for Explanation Requests in Customer-Care Domain. In 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, pages 5–10, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Content Selection for Explanation Requests in Customer-Care Domain (Anselma et al., NL4XAI 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.nl4xai-1.3.pdf