Data2Concept2Text: An Explainable Multilingual Framework for Data Analysis Narration

TL;DR

This paper introduces an explainable, multilingual system that interprets data by extracting concepts and translating them into natural language using logic-based rules, enhancing trustworthiness and accessibility in critical applications.

Contribution

It develops a transparent, rule-based framework for data-to-text generation that leverages logic programming and ontology reasoning, advancing explainability in natural language generation.

Findings

Demonstrates flexible multilingual natural language generation.

Shows the system can produce diverse, equivalent rewritings.

Highlights the importance of explainability in data interpretation.

Abstract

This paper presents a complete explainable system that interprets a set of data, abstracts the underlying features and describes them in a natural language of choice. The system relies on two crucial stages: (i) identifying emerging properties from data and transforming them into abstract concepts, and (ii) converting these concepts into natural language. Despite the impressive natural language generation capabilities demonstrated by Large Language Models, their statistical nature and the intricacy of their internal mechanism still force us to employ these techniques as black boxes, forgoing trustworthiness. Developing an explainable pipeline for data interpretation would allow facilitating its use in safety-critical environments like processing medical information and allowing non-experts and visually impaired people to access narrated information. To this end, we believe that the fields of knowledge representation and automated reasoning research could present a valid alternative. Expanding on prior research that tackled the first stage (i), we focus on the second stage, named Concept2Text. Being explainable, data translation is easily modeled through logic-based rules, once again emphasizing the role of declarative programming in achieving AI explainability. This paper explores a Prolog/CLP-based rewriting system to interpret concepts-articulated in terms of classes and relations, plus common knowledge-derived from a generic ontology, generating natural language text. Its main features include hierarchical tree rewritings, modular multilingual generation, support for equivalent variants across semantic, grammar, and lexical levels, and a transparent rule-based system. We outline the architecture and demonstrate its flexibility through some examples capable of generating numerous diverse and equivalent rewritings based on the input concept.