Designing generalisation evaluation function through human-machine dialogue

TL;DR

This paper introduces a novel human-machine dialogue-based method for designing evaluation functions to automatically assess data generalisation, improving their accuracy through iterative user feedback and machine learning.

Contribution

It presents a new approach that refines generalisation evaluation functions via user preferences and machine learning, enhancing automatic assessment accuracy.

Findings

Significant improvement in evaluation functions through dialogue-based revisions

Effective use of machine learning to incorporate user preferences

Validated on building data with positive results

Abstract

Automated generalisation has known important improvements these last few years. However, an issue that still deserves more study concerns the automatic evaluation of generalised data. Indeed, many automated generalisation systems require the utilisation of an evaluation function to automatically assess generalisation outcomes. In this paper, we propose a new approach dedicated to the design of such a function. This approach allows an imperfectly defined evaluation function to be revised through a man-machine dialogue. The user gives its preferences to the system by comparing generalisation outcomes. Machine Learning techniques are then used to improve the evaluation function. An experiment carried out on buildings shows that our approach significantly improves generalisation evaluation functions defined by users.