An xAI Approach for Data-to-Text Processing with ASP

TL;DR

This paper introduces an explainable AI framework for data-to-text generation using ASP/Python, enabling explicit control over accuracy and synthesis, with hierarchical text organization and logic-based structure management.

Contribution

It presents a novel xAI approach employing ASP/Python to control data-to-text generation, ensuring accuracy and coherence with hierarchical, logic-driven text structuring.

Findings

Framework allows explicit control of accuracy errors.

Hierarchical, logic-based text organization.

Proven optimal solutions for data-to-text tasks.

Abstract

The generation of natural language text from data series gained renewed interest among AI research goals. Not surprisingly, the few proposals in the state of the art are based on training some system, in order to produce a text that describes and that is coherent to the data provided as input. Main challenges of such approaches are the proper identification of "what" to say (the key descriptive elements to be addressed in the data) and "how" to say: the correspondence and accuracy between data and text, the presence of contradictions/redundancy in the text, the control of the amount of synthesis. This paper presents a framework that is compliant with xAI requirements. In particular we model ASP/Python programs that enable an explicit control of accuracy errors and amount of synthesis, with proven optimal solutions. The text description is hierarchically organized, in a top-down structure where text is enriched with further details, according to logic rules. The generation of natural language descriptions' structure is also managed by logic rules.