Artificial Intelligence and Law最新文献

{"title":"Mining EU consultations through AI","authors":"Fabiana Di Porto,&nbsp;Paolo Fantozzi,&nbsp;Maurizio Naldi,&nbsp;Nicoletta Rangone","doi":"10.1007/s10506-024-09426-6","DOIUrl":"10.1007/s10506-024-09426-6","url":null,"abstract":"<div><p>Consultations are key to gather evidence that informs rulemaking. When analysing the feedback received, it is essential for the regulator to appropriately cluster stakeholders’ opinions, as misclustering may alter the representativeness of the positions, making some of them appear majoritarian when they might not be. The European Commission (EC)’s approach to clustering opinions in consultations lacks a standardized methodology, leading to reduced procedural transparency, while making use of computational tools only sporadically. This paper explores how natural language processing (NLP) technologies may enhance the way opinion clustering is currently conducted by the EC. We examine 830 responses to three legislative proposals (the Artificial Intelligence Act, the Digital Markets Act and the Digital Services Act) using both a lexical and semantic approach. We find that some groups (like small and medium companies) have low similarity across all datasets and methodologies despite being clustered in one opinion group by the EC. The same happens for citizens and consumer associations for the consultation run over the DSA. These results suggest that computational tools actually help reduce misclustering of stakeholders’ opinions and consequently allow greater representativeness of the different positions expressed in consultations. They further suggest that the EC could identify a convergent methodology for all its consultations, where such tools are employed in a consistent and replicable rather than occasionally. Ideally, it should also explain when one methodology is preferred to another. This effort should find its way into the Better Regulation toolbox (EC 2023). Our analysis also paves the way for further research to reach a transparent and consistent methodology for group clustering.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 1","pages":"267 - 304"},"PeriodicalIF":3.1,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10506-024-09426-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147562013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LaCour!: enabling research on argumentation in hearings of the European Court of Human Rights","authors":"Lena Held,&nbsp;Ivan Habernal","doi":"10.1007/s10506-024-09428-4","DOIUrl":"10.1007/s10506-024-09428-4","url":null,"abstract":"<div><p>Why does an argument end up in the final court decision? Was it deliberated or questioned during the oral hearings? Was there something in the hearings that triggered a particular judge to write a dissenting opinion? Despite the availability of the final judgments of the European Court of Human Rights (ECHR), none of these legal research questions can currently be answered as the ECHR’s multilingual oral hearings are not transcribed, structured, or speaker-attributed. We address this fundamental gap by presenting LaCour!, the first corpus of textual oral arguments of the ECHR, consisting of 154 full hearings (2.1 million tokens from over 267 h of video footage) in English, French, and other court languages, each linked to the corresponding final judgment documents. In addition to the transcribed and partially manually corrected text from the video, we provide sentence-level timestamps and manually annotated role and language labels. We also showcase LaCour! in a set of experiments that explore the interplay between questions and dissenting opinions. Apart from the use cases in legal NLP, we hope that law students or other interested parties will also use LaCour! as a learning resource, as it is freely available in various formats at https://huggingface.co/datasets/TrustHLT/LaCour.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 2","pages":"311 - 334"},"PeriodicalIF":3.1,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10506-024-09428-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147967980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deciphering disagreement in the annotation of EU legislation","authors":"Gijs van Dijck,&nbsp;Carlos Aguilera,&nbsp;Shashank M. Chakravarthy","doi":"10.1007/s10506-024-09423-9","DOIUrl":"10.1007/s10506-024-09423-9","url":null,"abstract":"<div><p>The topic of annotating legal data has received surprisingly little attention. A key challenge of the annotation process is reaching a sufficient agreement between annotators and filtering mistakes from genuine disagreement. This study presents an approach that provides insights into and resolves potential disagreement amongst annotators. It (1) introduces different strategies to calculate agreement levels and compares (2) agreement levels between annotators (inter-annotator agreement) before and after a revision round and (3) agreement levels for annotators who annotate the same texts twice (intra-annotator agreement). The inter-annotator agreement levels are compared to a revision round in which an arbiter corrected the annotator’s labels. The analysis is based on the annotation of EU legislative provisions at two stages (initial annotations, after annotator revisions) and for various tasks (Definitions, References, Quantities, IF-THEN statements, Exceptions, Scope, Hierarchy, Deontic Clauses, Active and Passive Role) by multiple annotators. The results reveal that agreement levels vary based on the stage of measurement (before/after revisions), the nature of the task, the method of assessment, and the annotator combination. The agreement scores - along with some initial measurements—align with those reported in previous research but increase after each revision round. This suggests that annotator revisions can substantially reduce disagreement. Additionally, disagreements were found not only between but also among annotators. This inconsistency does not appear to stem from a lack of understanding of the guidelines or a lack of seriousness in task execution, as evidenced by moderate to substantial inter-annotator agreement scores. These findings suggest that annotators identified multiple valid interpretations, which highlights the complexity of annotating legislative provisions. The results underscore the significance of embracing, addressing, and reporting about (dis)agreement in different ways and at the various stages of an annotation task.\u0000</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 1","pages":"191 - 226"},"PeriodicalIF":3.1,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10506-024-09423-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147559529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A case study for automated attribute extraction from legal documents using large language models","authors":"Subinay Adhikary,&nbsp;Procheta Sen,&nbsp;Dwaipayan Roy,&nbsp;Kripabandhu Ghosh","doi":"10.1007/s10506-024-09425-7","DOIUrl":"10.1007/s10506-024-09425-7","url":null,"abstract":"<div><p>The escalating number of pending cases is a growing concern worldwide. Recent advancements in digitization have opened up possibilities for leveraging artificial intelligence (AI) tools in the processing of legal documents. Adopting a structured representation for legal documents, as opposed to a mere bag-of-words flat text representation, can significantly enhance processing capabilities. With the aim of achieving this objective, we put forward a set of diverse attributes for criminal case proceedings. To enhance the effectiveness of automatically extracting these attributes from legal documents within a sequence labeling framework, we propose the utilization of a few-shot learning approach based on Large Language Models (LLMs). Moreover, we demonstrate the efficacy of the extracted attributes in downstream tasks, such as <i>legal judgment prediction and legal statute prediction</i>.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 1","pages":"245 - 266"},"PeriodicalIF":3.1,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10506-024-09425-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147558841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing legal recommendation system with enhanced Bayesian network machine learning","authors":"Xukang Wang,&nbsp;Vanessa Hoo,&nbsp;Mingyue Liu,&nbsp;Jiale Li,&nbsp;Ying Cheng Wu","doi":"10.1007/s10506-024-09424-8","DOIUrl":"10.1007/s10506-024-09424-8","url":null,"abstract":"<div><p>The integration of machine learning algorithms into the legal recommendation system marks a burgeoning area of research, with a particular focus on enhancing the accuracy and efficiency of judicial decision-making processes. The application of Bayesian Network (BN) emerges as a potent tool in this context, promising to address the inherent complexities and unique nuances of legal texts and individual case subtleties. However, the challenge of achieving high accuracy in BN parameter learning, especially under conditions of limited data, remains a significant hurdle. This study proposes an Enhanced Maximum Parameter Learning (EMPL) algorithm, tailored for BN parameter optimization in scenarios characterized by small sample sizes. The EMPL algorithm, innovatively incorporating the Synthetic Minority Over-sampling Technique (SMOTE), begins with the formulation of inequality constraints derived from domain expertise. It establishes a minimal dataset threshold necessary for effective parameter learning. Through the introduction of an index weighting factor function that dynamically adjusts according to the sample size, the algorithm facilitates the derivation of refined BN parameters. The core innovation of the EMPL algorithm lies in its use of an exponentially weighted factor function, designed to be responsive to variations in sample size, and its capacity to expand the parameter space using SMOTE to align with qualitative constraints from expert insights. This approach enables the integration of data-derived parameters with those obtained through expert experience in an exponentially weighted manner, culminating in the optimization of BN parameters. Comparative analysis reveals that the EMPL algorithm achieves superior learning accuracy over traditional Maximum Likelihood Estimation (MLE) and qualitative maximum a posteriori (QMAP) approach, particularly in contexts of sparse data. Furthermore, it demonstrates enhanced performance relative to variable weight learning algorithms, underscoring its potential to significantly improve decision-making processes in the legal domain through advanced BN parameter learning.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 1","pages":"227 - 244"},"PeriodicalIF":3.1,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147558680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to: The digital transformation of jurisprudence: an evaluation of ChatGPT-4’s applicability to solve cases in business law","authors":"Sascha Schweitzer,&nbsp;Markus Conrads","doi":"10.1007/s10506-024-09417-7","DOIUrl":"10.1007/s10506-024-09417-7","url":null,"abstract":"","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 1","pages":"305 - 309"},"PeriodicalIF":3.1,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10506-024-09417-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147559482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Segmenting Brazilian legislative text using weak supervision and active learning","authors":"Felipe A. Siqueira,&nbsp;Diany Pressato,&nbsp;Fabíola S. F. Pereira,&nbsp;Nádia F. F. da Silva,&nbsp;Ellen Souza,&nbsp;Márcio S. Dias,&nbsp;André C. P. L. F. de Carvalho","doi":"10.1007/s10506-024-09419-5","DOIUrl":"10.1007/s10506-024-09419-5","url":null,"abstract":"<div><p>Legislative houses all over the world are adopting tools based on artificial intelligence to support their work. The incorporation of these tools can improve the analysis of the text of the proposed new laws and speed the preparation and discussion of new laws. The performance of artificial intelligence tools for text processing tasks is largely affected by the corpora used, which should ideally be adapted for the specific domain. When dealing with legislative corpora, text segmentation is often necessary due to the distinct purposes of legislative segments within the overall bill structure. While rule-based approaches can be effective in cases where the data follows a consistent format, they fail when inconsistencies arise in the formatting of legislative bills. In this study, we extensively investigate the use of weak supervision and active learning to accurately segment over 100,000 Brazilian federal legislative bills using a sequence tagging approach. The experiments demonstrated that both BERT and LSTM models achieved high statistical performance without the limitations of rule-based systems. In segmenting long documents beyond the limited context window of BERT, we find that simple moving windows suffice because the required context for accurate legislative segmentation is mostly local. We also conducted an analysis of transfer learning from our monolingual models to French, Italian, German, and English (US) legislative texts. According to our experimental results our models present non-trivial zero-shot and effective out-of-distribution fine-tuning performance, suggesting potential avenues for multilingual legislative segmentation without the need for computationally expensive models. The models, data, and code are publicly available at https://github.com/ulysses-camara/ulysses-segmenter.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 1","pages":"1 - 82"},"PeriodicalIF":3.1,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147561888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"System for the anonymization of Romanian jurisprudence","authors":"Vasile Păiş,&nbsp;Radu Ion,&nbsp;Elena Irimia,&nbsp;Verginica Barbu Mititelu,&nbsp;Valentin Badea,&nbsp;Dan Tufiș","doi":"10.1007/s10506-024-09420-y","DOIUrl":"10.1007/s10506-024-09420-y","url":null,"abstract":"<div><p>The transparency of the judicial process and the consistency of judicial decisions can be improved through their publication. Access to jurisprudence is of paramount importance both for law professionals (judges, lawyers, law students) and for the larger public. However, public access must ensure the preservation of privacy for people involved, in accordance with national and international regulations. This paper presents the work behind building an artificial intelligence system for the anonymization of Romanian jurisprudence, allowing it to be accessed through the ReJust portal operated by the Superior Council of Magistracy in Romania.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"34 1","pages":"83 - 105"},"PeriodicalIF":3.1,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147559196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LAWSUIT: a LArge expert-Written SUmmarization dataset of ITalian constitutional court verdicts","authors":"Luca Ragazzi,&nbsp;Gianluca Moro,&nbsp;Stefano Guidi,&nbsp;Giacomo Frisoni","doi":"10.1007/s10506-024-09414-w","DOIUrl":"10.1007/s10506-024-09414-w","url":null,"abstract":"<div><p>Large-scale public datasets are vital for driving the progress of abstractive summarization, especially in law, where documents have highly specialized jargon. However, the available resources are English-centered, limiting research advancements in other languages. This paper introduces <span>LAWSUIT</span>, a collection of 14K Italian legal verdicts with expert-authored abstractive maxims drawn from the Constitutional Court of the Italian Republic. <span>LAWSUIT</span> presents an arduous task with lengthy source texts and evenly distributed salient content. We offer extensive experiments with sequence-to-sequence and segmentation-based approaches, revealing that the latter achieve better results in full and few-shot settings. We openly release <span>LAWSUIT</span> to foster the development and automation of real-world legal applications.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"33 4","pages":"1151 - 1187"},"PeriodicalIF":3.1,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10506-024-09414-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145493398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DGGCCM: a hybrid neural model for legal event detection","authors":"Shutao Gong,&nbsp;Xudong Luo","doi":"10.1007/s10506-024-09418-6","DOIUrl":"10.1007/s10506-024-09418-6","url":null,"abstract":"<div><p>This paper introduces an advanced event detection model for legal intelligence, focusing on identifying event types in legal cases by examining trigger word candidates. It employs the DeBERTa pre-trained language model for encoding sentences into enriched word representations, supplemented by the Global Pointer neural network for initial scoring. The model further uses a graph convolutional network, conditional layer normalisation, and a convolutional neural network to extract features from these representations. A multilayer perceptron then determines the event type based on these features and initial scores. Additionally, a dictionary-matching method revises the predicted event types, with adversarial training and a sentence-length mask employed to enhance model performance and address missing trigger words. The model’s effectiveness is proven through extensive experimentation, outperforming state-of-the-art baselines (including some large language models) and securing third prize in the event detection task at the Challenge of AI in Law (CAIL) 2022. The code of our model is available at https://github.com/1gst/DGGCCN/tree/main.</p></div>","PeriodicalId":51336,"journal":{"name":"Artificial Intelligence and Law","volume":"33 4","pages":"1109 - 1149"},"PeriodicalIF":3.1,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145493397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}