Abstract
We approach the problem of interpretability for fuzzy linguistic descriptions of data from a natural language generation perspective. For this, first we review the current state of linguistic descriptions of data and their use contexts as a standalone tool and as part of a natural language generation system. Then, we discuss the standard approach to interpretability for linguistic descriptions and introduce our complementary proposal, which describes the elements from linguistic descriptions of data that can influence and improve the interpretability of automatically generated texts (such as fuzzy properties, quantifiers, and truth degrees), when linguistic descriptions are used to determine relevant content within a text generation system.
Original language | English |
---|---|
Title of host publication | Information Processing and Management of Uncertainty in Knowledge-Based Systems |
Subtitle of host publication | Theory and Foundations. IPMU 2018 |
Editors | J Medina, M Ojeda-Aciego, J L Verdegay, J L Pelta, I P Cabrera, B Bouchon-Meunier, R R Yager |
Place of Publication | Cham |
Publisher | Springer |
Pages | 40-51 |
Number of pages | 12 |
ISBN (Electronic) | 978-3-319-91473-2 |
ISBN (Print) | 978-3-319-91472-5 |
DOIs | |
Publication status | Published - 2018 |
Event | 17th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems - Cádiz, Spain Duration: 11 Jun 2018 → 15 Jun 2018 Conference number: 17 http://ipmu2018.uca.es/ |
Publication series
Name | Communications in Computer and Information Science |
---|---|
Publisher | Springer |
Number | 853 |
ISSN (Print) | 1865-0929 |
Conference
Conference | 17th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems |
---|---|
Abbreviated title | IPMU 2018 |
Country/Territory | Spain |
City | Cádiz |
Period | 11/06/18 → 15/06/18 |
Internet address |
Keywords
- fuzzy sets
- linguistic summarization
- fuzzy linguistic descriptions of data
- interpretability
- natural language generation
- data-to-text