Abstract
This paper presents the problem statement and the research approach on an Italian project in the field of e-justice. We present the motivation and methodology for the application of an automatic writing assistant pipeline to Italian civil cases. The proposed solution is based on fine-tuning a transformer on a pre-processed corpus of Italian civil judgments. The resulting language model may be deployed as a writing assistant for legal users, in order to improve the efficiency of text writing, or further fine-tuned to be deployed in other law-related NLP tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In the recent Italian reform of the Italian judicial offices, a new function was created, named “Ufficio per il Processo” (in Italian, in English it might be “Office for the Judicial Process”).
- 2.
- 3.
Cicero, the well-known politician and writer in the ancient Rome, was also a lawyer appreciated for his eloquence.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
Actually, one could interpret de-instantiation as a type of masking [2], where, rather than using an anonymous mask, a semi-anonymous NER token is deployed.
- 10.
- 11.
- 12.
- 13.
- 14.
- 15.
ChatGPT is an AI-based chatbot model developed by OpenAI that specializes in conversations with a human user.
References
Anandarajan, M., Hill, C., Nolan, T.: Text Preprocessing. In: Anandarajan, M., Hill, C., Nolan, T., et al. (eds.) Practical Text Analytics. AADS, vol. 2, pp. 45–59. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-95663-3_4
Bao, H., et al.: UniLMv2: pseudo-masked language models for unified language model pre-training. In: International Conference on Machine Learning, pp. 642–652. PMLR (2020)
Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Aletras, N., Androutsopoulos, I.: LEGAL-BERT: the muppets straight out of law school. arXiv preprint arXiv:2010.02559 (2020)
Council of Europe: European judicial systems: efficiency and quality of justice. CEPEJ Stud. 26, 1–338 (2018)
Dale, R., Viethen, J.: The automated writing assistance landscape in 2021. Nat. Lang. Eng. 27(4), 511–518 (2021)
De Mattei, L., Cafagna, M., Dell’Orletta, F., Nissim, M., Guerini, M.: GePpeTto carves Italian into a language model. In: 7th Italian Conference on Computational Linguistics, CLiC-it 2020 (2020)
Di Martino, B., Marulli, F., Lupi, P., Cataldi, A.: A machine learning based methodology for automatic annotation and anonymisation of privacy-related items in textual documents for justice domain. In: Barolli, L., Poniszewska-Maranda, A., Enokido, T. (eds.) CISIS 2020. AISC, vol. 1194, pp. 530–539. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-50454-0_55
Johannesson, P., Perjons, E.: An Introduction to Design Science. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10632-8
Kalyan, K.S., Rajasekharan, A., Sangeetha, S.: AMMUS: a survey of transformer-based pretrained models in natural language processing. arXiv preprint arXiv:2108.05542 (2021)
van der Lee, C., Gatt, A., van Miltenburg, E., Krahmer, E.: Human evaluation of automatically generated text: current trends and best practice guidelines. Comput. Speech Lang. 67, 101151 (2021)
Leivaditi, S., Rossi, J., Kanoulas, E.: A benchmark for lease contract review. arXiv preprint arXiv:2010.10386 (2020)
Lin, T., Wang, Y., Liu, X., Qiu, X.: A survey of transformers. AI Open 3, 111–132 (2022)
Lippi, M., et al.: CLAUDETTE: an automated detector of potentially unfair clauses in online terms of service. Artif. Intell. Law 27(2), 117–139 (2019). https://doi.org/10.1007/s10506-019-09243-2
Mahajan, N.: E-governance: its role, importance and challenges. Int. J. Curr. Innov. Res. 1(10), 237–243 (2015)
Peric, L., Mijic, S., Stammbach, D., Ash, E.: Legal language modeling with transformers. In: 4th Workshop on Automated Semantic Analysis of Information in Legal Text (ASAIL 2020), vol. 2764. CEUR-WS (2020)
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)
Sarti, G., Nissim, M.: IT5: large-scale text-to-text pretraining for Italian language understanding and generation (2022)
Tagarelli, A., Simeri, A.: Unsupervised law article mining based on deep pre-trained language representation models with application to the Italian civil code. Artif. Intell. Law 30, 417–473 (2022). https://doi.org/10.1007/s10506-021-09301-8
de Vries, W., Nissim, M.: As good as new. How to successfully recycle English GPT-2 to make models for other languages. arXiv preprint arXiv:2012.05628 (2020)
Zhao, W.X., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)
Acknowledgements
This work is partially funded by the PE1 - FAIR (Future Artificial Intelligence Research) - European Union Next-Generation-EU (Piano Nazionale di Ripresa e Resilienza - PNRR), and by the Italian Ministry of Justice PON project “Per una Giustizia giusta: Innovazione ed efficienza negli uffici giudiziari - Giustizia Agile”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
De Luzi, F., Macrì, M., Mecella, M., Mencattini, T. (2023). Cicero: An AI-Based Writing Assistant for Legal Users. In: Cabanillas, C., Pérez, F. (eds) Intelligent Information Systems. CAiSE 2023. Lecture Notes in Business Information Processing, vol 477. Springer, Cham. https://doi.org/10.1007/978-3-031-34674-3_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-34674-3_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34673-6
Online ISBN: 978-3-031-34674-3
eBook Packages: Computer ScienceComputer Science (R0)