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.
An xAI Approach for Data-to-Text Processing with ASP / Dal Palu, A.; Dovier, A.; Formisano, A.. - 385:385(2023), pp. 353-366. (Intervento presentato al convegno 39th International Conference on Logic Programming, ICLP 2023 tenutosi a Imperial College London, gbr nel 2023) [10.4204/EPTCS.385.38].
An xAI Approach for Data-to-Text Processing with ASP
Dal Palu A.;Dovier A.;Formisano A.
2023-01-01
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.