Exploiting ChatGPT to simplify Italian bureaucratic and professional texts
DOI:
https://doi.org/10.62408/ai-ling.v1i1.13Keywords:
Large Language Models, ChatGPT, Bureaucratic and professional texts, Rephrasing, Prompt EngineeringAbstract
This paper investigates the use of ChatGPT, a large language model, for simplifying long sentences and nominal clusters in professional texts belonging to administrative and legal domains. We apply three prompt engineering techniques — zero-shot learning, few-shot learning, and Chain-of-Thought reasoning — to generate alternative sentences from a corpus of Italian texts. We evaluate the generated sentences using a survey with expert and non-expert readers of bureaucratic and legal Italian, focusing on ease of understanding, coherence, and preferences in rephrasing. Our results show that ChatGPT can effectively address the linguistic challenges outlined by UNI 11482:2013 Standard, and that complex prompting techniques yield better outcomes than simpler ones. We also discuss the implications of our findings for the optimization of text understanding and simplification using large language models.
References
Acerboni, Giovanni & Panunzi, Alessandro. 2020. La scrittura professionale. In Baldi, Benedetta (ed.), Comunicare ad arte per costruire contenuti e promuovere eventi, 221–236. Bologna: Zanichelli.
Al-Thanyyan, Suha & Azmi, Aqil. 2021. Automated text simplification: a survey. ACM Computing Surveys 54(2). 1–36. https://doi.org/10.1145/3442695.
Barlacchi, Gianni & Tonelli, Sara. 2013. Ernesta: A Sentence Simplification Tool for Children’s Stories in Italian. In Gelbukh, Alexander (ed.), Computational Linguistics and Intelligent Text Processing. Proceedings of the 14th International Conference CICLing 2013 (Samos, March 24-30, 2013), 476–487. Berlin: Springer. https://doi.org/10.1007/978-3-642-37256-8_39.
Bott, Stefan & Saggion, Horacio. 2012. Automatic simplification of Spanish text for e-accessibility. In Miesenberger, Klaus & Karshmer, Arthur & Penaz, Petr & Zagler, Wolfgang (eds), Computers Helping People with Special Needs. Lecture Notes in Computer Science 7382. 527–534. Berlin-Heidelberg: Springer. https://doi.org/10.1007/978-3-642-31522-0_79.
Brown, Tom & Mann, Benjamin & Ryder, Nick & Subbiah, Melanie & Kaplan, Jared & Dhariwal, Prafulla & Neelakantan, Arvind & Shyam, Pranav & Sastry Girish & Askell, Amanda et al. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33. 1877–1901.
Cassese, Sabino. 1994. Codice di stile delle comunicazioni scritte ad uso delle pubbliche amministrazioni. Proposta e materiali di studio. Quaderni del Dipartimento per la Funzione Pubblica, n. 8. Roma, Istituto Poligrafico e Zecca dello Stato, Libreria dello Stato.
Chen, Banghao & Zhang, Zhaofeng & Langrené, Nicolas & Zhu, Shengxin. 2023. Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review. ArXiv. https://doi.org/10.48550/arXiv.2310.14735 (last accessed on 16/07/2024)
Cortelazzo, Michele & Pellegrino, Federica. 2003. Guida alla scrittura istituzionale. Bari: Laterza. http://hdl.handle.net/11577/1340740.
Covino, Sandra. 2001. La scrittura professionale. Ricerca, prassi, insegnamento, Atti del I Convegno di Studi (Perugia, October 23-25, 2000). Firenze: Olschki Editore.
Dell’Orletta, Felice & Montemagni, Simonetta & Venturi, Giulia. 2011. READ–IT: Assessing readability of Italian texts with a view to text simplification. In Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies (Edinburgh, July 30, 2011), 73–83. Edinburgh: Association for Computational Linguistics.
Feng, Yutao & Qiang, Jipeng & Li, Yun & Yuan, Yunhao & Zhu, Yi. 2023. Sentence simplification via large language models. ArXiv. arXiv:2302.11957 (last accessed on 16/07/2024)
Gualdo, Riccardo & Telve, Stefano. 2011. Linguaggi specialistici dell’italiano. Roma: Carocci.
Lucisano, Pietro & Piemontese, Maria Emanuela. 1988. Gulpease: una formula per la predizione della leggibilità di testi in lingua italiana. Scuola e città. 110–124. . http://hdl.handle.net/11573/450554.
Megna, Angelo Luigi & Schicchi, Daniele & Lo Bosco, Giosuè & Pilato, Giovanni. 2021. A controllable text simplification system for the Italian language. In 2021 IEEE 15th International Conference on Semantic Computing (ICSC) (Laguna Hills, January 27-29, 2021), 191–194. https://doi.org/10.1109/ICSC50631.2021.00040.
Mortara Garavelli, Bice. 2001. Le parole e la giustizia, Divagazioni grammaticali e retoriche su testi giuridici italiani. Torino: Einaudi.
North, Kai & Ranasinghe, Tharindu & Shardlow, Matthew & Zampieri, Marco. 2023. Deep Learning approaches to lexical simplification: A survey. ArXiv. arXiv:2305.12000. (last accessed on 16/07/2024)
Nozza, Debora, & Attanasio, Giuseppe. 2023. Is it really that simple? Prompting Language Models for Automatic Text Simplification in Italian. In Boschetti, Federico & Lebani, Gianluca E. & Novielli, Nicole (eds), Proceedings of the 9th Italian Conference on Computational Linguistics CLiC-it 2023 (Venezia, November 30-December 2, 2023).
Palmero Aprosio, Alessio & Tonelli, Sara & Turchi, Marco & Negri, Matteo & Di Gangi, Mattia. 2019. Neural text simplification in low-resource conditions using weak supervision. In Proceedings of the NeuralGen Workshop: Methods for Optimizing and Evaluating Neural Language Generation (Minneapolis, June 6, 2019), 37–44. Association for Computational Linguistics. https://doi.org/10.18653/v1/W19-2305.
Raso, Tommaso. 2005. La scrittura burocratica. La lingua e l’organizzazione del testo. Roma: Carocci.
Saggion, Horacio. 2017. Automatic text simplification. In Hirst, Graeme (ed.), Synthesis lectures on Human-Language Technologies. Toronto: Morgan & Claypool Publishers. https://doi.org/10.1007/978-3-031-02166-4.
Scarton, Carolina & Palmero Aprosio, Alessio & Tonelli, Sara & Wanton Martín, Tamara & Specia, Lucia. 2017. MUSST: A multilingual syntactic simplification tool. In Proceedings of the International Joint Conference on Natural Language Processing IJCNLP 2017, System Demonstrations (Tapei, 27 November – 1 December 2017), 25–28. Association for Computational Linguistics.
Shardlow, Matthew. 2014. A survey of automated text simplification. International Journal of Advanced Computer Science and Applications 4(1), 58–70. https://doi.org/10.14569/SpecialIssue.2014.040109.
Wei, Jason & Bosma, Maarten & Zhao, Vincent Y. & Guu, Kelvin & Wei Yu, Adams & Lester, Brian & Du, Nan & Dai, Andrew M. & Le, Quoc V. 2021. Finetuned language models are zero-shot learners. ArXiv. https://doi.org/10.48550/arXiv.2109.01652
Wei, Jason & Xuezhi, Wang & Schuurmans, Dale & Bosma, Maarten & Ichter, Brian & Xia, Fei & Chi, Ed & Le, Quoc & Zhou, Denny. 2022. Chain-of-thought prompting elicits reasoning in large language models. ArXiv. https://doi.org/10.48550/arXiv.2201.11903. (last accessed on 16/07/2024)
Downloads
Published
Versions
- 2025-04-14 (2)
- 2024-08-07 (1)
How to Cite
Issue
Section
License
Copyright (c) 2024 Walter Paci, Lorenzo Gregori, Giovanni Acerboni, Alessandro Panunzi, Maria Roberta Perugini
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
