Cicero: An AI-Based Writing Assistant for Legal Users

被引:2
作者
De Luzi, Francesca [1 ]
Macri, Mattia [1 ]
Mecella, Massimo [1 ]
Mencattini, Tommaso [1 ]
机构
[1] Sapienza Univ Roma, Rome, Italy
来源
INTELLIGENT INFORMATION SYSTEMS, CAISE FORUM 2023 | 2023年 / 477卷
关键词
e-justice; legal text generation; language models;
D O I
10.1007/978-3-031-34674-3_13
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:103 / 111
页数:9
相关论文
共 20 条
[11]  
Leivaditi S, 2020, Arxiv, DOI [arXiv:2010.10386, DOI 10.48550/ARXIV.2010.10386]
[12]   A survey of transformers [J].
Lin, Tianyang ;
Wang, Yuxin ;
Liu, Xiangyang ;
Qiu, Xipeng .
AI OPEN, 2022, 3 :111-132
[13]   CLAUDETTE: an automated detector of potentially unfair clauses in online terms of service [J].
Lippi, Marco ;
Palka, Przemyslaw ;
Contissa, Giuseppe ;
Lagioia, Francesca ;
Micklitz, Hans-Wolfgang ;
Sartor, Giovanni ;
Torroni, Paolo .
ARTIFICIAL INTELLIGENCE AND LAW, 2019, 27 (02) :117-139
[14]  
Mahajan N., 2015, Int. J. Curr. Innov. Res., V1, P237
[15]  
Peric L., 2020, 4 WORKSH AUT SEM AN, V2764
[16]  
Radford A., 2019, Language Models are Unsupervised Multitask Learners
[17]  
Sarti G., 2022, IT5: large-scale text-to-text pretraining for Italian language understanding and generation
[18]   Unsupervised law article mining based on deep pre-trained language representation models with application to the Italian civil code [J].
Tagarelli, Andrea ;
Simeri, Andrea .
ARTIFICIAL INTELLIGENCE AND LAW, 2022, 30 (03) :417-473
[19]   Human evaluation of automatically generated text: Current trends and best practice guidelines [J].
van der Lee, Chris ;
Gatt, Albert ;
van Miltenburg, Emiel ;
Krahmer, Emiel .
COMPUTER SPEECH AND LANGUAGE, 2021, 67
[20]  
Zhao WX, 2024, Arxiv, DOI arXiv:2303.18223