Process-To-Text: A Framework for the Quantitative Description of Processes in Natural Language
This work addresses the need for natural language explanations of processes for specialists, but it appears incremental as it combines existing AI paradigms without claiming major breakthroughs.
The paper tackles the problem of automatically generating textual explanations of processes by introducing the Process-To-Text (P2T) framework, which integrates process mining, fuzzy linguistic protoforms, and natural language generation, and demonstrates its potential in a cardiology use-case for specialists.
In this paper we present the Process-To-Text (P2T) framework for the automatic generation of textual descriptive explanations of processes. P2T integrates three AI paradigms: process mining for extracting temporal and structural information from a process, fuzzy linguistic protoforms for modelling uncertain terms, and natural language generation for building the explanations. A real use-case in the cardiology domain is presented, showing the potential of P2T for providing natural language explanations addressed to specialists.