The recent improvement of powerful Large Language Models is the key to automatically produce satisfactory written and spoken language, in contrast to the constraints of conventional template-based solutions. However, the most advanced models can be costly and complex to integrate into practical applications, especially in business contexts where the output quality significantly matters. This study presents a tailored pipeline for data-to-text and text-to-speech generation, primarily harnessing the availability of open source pre-trained language models and leveraging established Natural Language Processing tasks. As a use case, we worked on the automatic generation of both textual and video product descriptions from the structured information about the product features. The pipeline involves all the required steps, providing the final trained and customized model. The obtained descriptions showed the capability of replicating the overall semantic, lexical and linguistic style of the corresponding human counterpart, despite being based on a cost-effective model.

From Product Sheet to Text and Video: A NLG Pipeline to Transform Structured Data into Comprehensive Descriptions / Avignone, Andrea; Fiori, Alessandro; Chiusano, Silvia; Rizzo, Giuseppe. - 3741:(2024), pp. 271-280. (Intervento presentato al convegno 32nd Symposium of Advanced Database Systems tenutosi a Villasimius (ITA) nel June 23rd to 26th, 2024).

From Product Sheet to Text and Video: A NLG Pipeline to Transform Structured Data into Comprehensive Descriptions

Andrea Avignone;Alessandro Fiori;Silvia Chiusano;
2024

Abstract

The recent improvement of powerful Large Language Models is the key to automatically produce satisfactory written and spoken language, in contrast to the constraints of conventional template-based solutions. However, the most advanced models can be costly and complex to integrate into practical applications, especially in business contexts where the output quality significantly matters. This study presents a tailored pipeline for data-to-text and text-to-speech generation, primarily harnessing the availability of open source pre-trained language models and leveraging established Natural Language Processing tasks. As a use case, we worked on the automatic generation of both textual and video product descriptions from the structured information about the product features. The pipeline involves all the required steps, providing the final trained and customized model. The obtained descriptions showed the capability of replicating the overall semantic, lexical and linguistic style of the corresponding human counterpart, despite being based on a cost-effective model.
File in questo prodotto:
File Dimensione Formato  
paper68.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 3.89 MB
Formato Adobe PDF
3.89 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2993082