Journal articles on the topic 'Legal dataset'
To see the other types of publications on this topic, follow the link: Legal dataset.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Legal dataset.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
KUNČIČ, ALJAŽ. "Institutional quality dataset." Journal of Institutional Economics 10, no. 1 (July 1, 2013): 135–61. http://dx.doi.org/10.1017/s1744137413000192.
Full textAbstract:
AbstractIn this paper, we emphasize the role of institutions as the underlying basis for economic and social activity. We describe and compare different institutional classification systems, which is rarely done in the literature, and show how to empirically operationalize institutional concepts. More than 30 established institutional indicators can be clustered into three homogeneous groups of formal institutions: legal, political and economic, which capture to a large extent the complete formal institutional environment of a country. We compute the latent quality of legal, political and economic institutions for every country in the world and for every year. On this basis, we propose a legal, political and economic World Institutional Quality Ranking, through which we can follow whether a country is improving or worsening its relative institutional environment. The calculated latent institutional quality measures can be especially useful in further panel data applications and add to the usual practice of using simply one or another index of institutional quality to capture the institutional environment. We make the Institutional Quality Dataset, covering up to 197 countries and territories from 1990 to 2010, freely available online.
2
Zhong, Haoxi, Chaojun Xiao, Cunchao Tu, Tianyang Zhang, Zhiyuan Liu, and Maosong Sun. "JEC-QA: A Legal-Domain Question Answering Dataset." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 9701–8. http://dx.doi.org/10.1609/aaai.v34i05.6519.
Full textAbstract:
We present JEC-QA, the largest question answering dataset in the legal domain, collected from the National Judicial Examination of China. The examination is a comprehensive evaluation of professional skills for legal practitioners. College students are required to pass the examination to be certified as a lawyer or a judge. The dataset is challenging for existing question answering methods, because both retrieving relevant materials and answering questions require the ability of logic reasoning. Due to the high demand of multiple reasoning abilities to answer legal questions, the state-of-the-art models can only achieve about 28% accuracy on JEC-QA, while skilled humans and unskilled humans can reach 81% and 64% accuracy respectively, which indicates a huge gap between humans and machines on this task. We will release JEC-QA and our baselines to help improve the reasoning ability of machine comprehension models. You can access the dataset from http://jecqa.thunlp.org/.
3
Ratnayaka, Gathika, Nisansa de Silva, Amal Shehan Perera, Gayan Kavirathne, Thirasara Ariyarathna, and Anjana Wijesinghe. "Context Sensitive Verb Similarity Dataset for Legal Information Extraction." Data 7, no. 7 (June 28, 2022): 87. http://dx.doi.org/10.3390/data7070087.
Full textAbstract:
Existing literature demonstrates that verbs are pivotal in legal information extraction tasks due to their semantic and argumentative properties. However, granting computers the ability to interpret the meaning of a verb and its semantic properties in relation to a given context can be considered as a challenging task, mainly due to the polysemic and domain specific behaviours of verbs. Therefore, developing mechanisms to identify behaviors of verbs and evaluate how artificial models detect the domain specific and polysemic behaviours of verbs can be considered as tasks with significant importance. In this regard, a comprehensive dataset that can be used as an evaluation resource, as well as a training data set, can be considered as a major requirement. In this paper, we introduce LeCoVe, which is a verb similarity dataset intended towards facilitating the process of identifying verbs with similar meanings in a legal domain specific context. Using the dataset, we evaluated both domain specific and domain generic embedding models, which were developed using state-of-the-art word representation and language modelling techniques. As a part of the experiments carried out using the announced dataset, Sense2Vec and BERT models were trained using a corpus of legal opinion texts in order to capture domain specific behaviours. In addition to LeCoVe, we demonstrate that a neural network model, which was developed by combining semantic, syntactic, and contextual features that can be obtained from the outputs of embedding models, can perform comparatively well, even in a low resource scenario.
4
Lin, Chun-Hsien, and Pu-Jen Cheng. "LARQS: An Analogical Reasoning Evaluation Dataset for Legal Word Embedding." International Journal on Natural Language Computing 11, no. 3 (June 30, 2022): 1–16. http://dx.doi.org/10.5121/ijnlc.2022.11301.
Full textAbstract:
Applying natural language processing-related algorithms is currently a popular project in legal applications, for instance, document classification of legal documents, contract review and machine translation. Using the above machine learning algorithms, all need to encode the words in the document in the form of vectors. The word embedding model is a modern distributed word representation approach and the most common unsupervised word encoding method. It facilitates subjecting other algorithms and subsequently performing the downstream tasks of natural language processing vis-à-vis. The most common and practical approach of accuracy evaluation with the word embedding model uses a benchmark set with linguistic rules or the relationship between words to perform analogy reasoning via algebraic calculation. This paper proposes establishing a 1,256 Legal Analogical Reasoning Questions Set (LARQS) from the 2,388 Chinese Codex corpus using five kinds of legal relations, which are then used to evaluate the accuracy of the Chinese word embedding model. Moreover, we discovered that legal relations might be ubiquitous in the word embedding model.
5
Shaheen, Z., D. I. Mouromtsev, and I. Postny. "RuLegalNER: a new dataset for Russian legal named entities recognition." Scientific and Technical Journal of Information Technologies, Mechanics and Optics 23, no. 4 (August 1, 2023): 854–57. http://dx.doi.org/10.17586/2226-1494-2023-23-4-854-857.
Full text
6
Owsiak, Andrew P., Allison K. Cuttner, and Brent Buck. "The International Border Agreements Dataset." Conflict Management and Peace Science 35, no. 5 (July 8, 2016): 559–76. http://dx.doi.org/10.1177/0738894216646978.
Full textAbstract:
We introduce a dataset that focuses on the delimitation of interstate borders under international law—the International Border Agreements Dataset (IBAD). This dataset contains information on the agents involved in (e.g. states, third-parties, and colonial powers), methods used during (e.g. negotiation, mediation, arbitration, adjudication, administrative decrees, post-war conferences, and plebiscites), and outcomes of (e.g. full and intermediate agreements) the border settlement process during the period 1816–2001. Our focus on international legal agreements and the process that produces them makes the IBAD valuable for those that study not only territorial conflict, but also international conflict, cooperation, law, and conflict management.
7
Crossfield, Samantha S. R., Kieran Zucker, Paul Baxter, Penny Wright, Jon Fistein, Alex F. Markham, Mark Birkin, Adam W. Glaser, and Geoff Hall. "A data flow process for confidential data and its application in a health research project." PLOS ONE 17, no. 1 (January 21, 2022): e0262609. http://dx.doi.org/10.1371/journal.pone.0262609.
Full textAbstract:
Background The use of linked healthcare data in research has the potential to make major contributions to knowledge generation and service improvement. However, using healthcare data for secondary purposes raises legal and ethical concerns relating to confidentiality, privacy and data protection rights. Using a linkage and anonymisation approach that processes data lawfully and in line with ethical best practice to create an anonymous (non-personal) dataset can address these concerns, yet there is no set approach for defining all of the steps involved in such data flow end-to-end. We aimed to define such an approach with clear steps for dataset creation, and to describe its utilisation in a case study linking healthcare data. Methods We developed a data flow protocol that generates pseudonymous datasets that can be reversibly linked, or irreversibly linked to form an anonymous research dataset. It was designed and implemented by the Comprehensive Patient Records (CPR) study in Leeds, UK. Results We defined a clear approach that received ethico-legal approval for use in creating an anonymous research dataset. Our approach used individual-level linkage through a mechanism that is not computer-intensive and was rendered irreversible to both data providers and processors. We successfully applied it in the CPR study to hospital and general practice and community electronic health record data from two providers, along with patient reported outcomes, for 365,193 patients. The resultant anonymous research dataset is available via DATA-CAN, the Health Data Research Hub for Cancer in the UK. Conclusions Through ethical, legal and academic review, we believe that we contribute a defined approach that represents a framework that exceeds current minimum standards for effective pseudonymisation and anonymisation. This paper describes our methods and provides supporting information to facilitate the use of this approach in research.
8
Baviskar, Dipali, Swati Ahirrao, and Ketan Kotecha. "Multi-Layout Invoice Document Dataset (MIDD): A Dataset for Named Entity Recognition." Data 6, no. 7 (July 20, 2021): 78. http://dx.doi.org/10.3390/data6070078.
Full textAbstract:
The day-to-day working of an organization produces a massive volume of unstructured data in the form of invoices, legal contracts, mortgage processing forms, and many more. Organizations can utilize the insights concealed in such unstructured documents for their operational benefit. However, analyzing and extracting insights from such numerous and complex unstructured documents is a tedious task. Hence, the research in this area is encouraging the development of novel frameworks and tools that can automate the key information extraction from unstructured documents. However, the availability of standard, best-quality, and annotated unstructured document datasets is a serious challenge for accomplishing the goal of extracting key information from unstructured documents. This work expedites the researcher’s task by providing a high-quality, highly diverse, multi-layout, and annotated invoice documents dataset for extracting key information from unstructured documents. Researchers can use the proposed dataset for layout-independent unstructured invoice document processing and to develop an artificial intelligence (AI)-based tool to identify and extract named entities in the invoice documents. Our dataset includes 630 invoice document PDFs with four different layouts collected from diverse suppliers. As far as we know, our invoice dataset is the only openly available dataset comprising high-quality, highly diverse, multi-layout, and annotated invoice documents.
9
Hidayat, Fahrul, and Rakyan Paksi Nagara. "DATASET BATAS WILAYAH ADMINISTRASI UNTUK PENATAAN RUANG WILAYAH." Seminar Nasional Geomatika 3 (February 15, 2019): 441. http://dx.doi.org/10.24895/sng.2018.3-0.984.
Full textAbstract:
Era desentralisasi politik Indonesia sudah berjalan selama 20 tahun namun permasalahan batas wilayah masih menjadi beban bagi pemerintah baik di tingkat pusat maupun daerah. Data Kementerian Dalam Negeri pada Januari 2018 menunjukkan bahwa batas wilayah administrasi daerah yang sudah memiliki dasar hukum adalah 48,47% atau 475 segmen. Persentase jumlah segmen yang masih dalam proses penegasan dan belum ditegaskan berturut - turut adalah 34,59% dan 16,94%. Batas wilayah seharusnya sudah jelas dan legal sebelum digunakan untuk proses administrasi suatu wilayah termasuk penataan ruang. Tujuan penelitian ini adalah untuk menilai kondisi eksisting penataan ruang wilayah beberapa provinsi di Indonesia dalam konteks pemanfaatan dataset batas wilayah administrasi daerah. Metode yang digunakan adalah (1) interpretasi visual terhadap dataset batas wilayah (vektor) dengan peta lampiran perda RTRW Provinsi (raster); dan (2) topology check terhadap dataset batas wilayah (vektor) dengan peta RTRW Provinsi (vektor). Hasil penelitian tersebut menunjukkan bahwa beberapa wilayah tidak menggunakan dataset batas wilayah administrasi daerah yang legal untuk penyusunan peta rencana tata ruang yaitu ditunjukkan dengan adanya gap dan overlap antarinformasi. Kesimpulan yang dapat diambil dari hasil penelitian adalah fungsi koordinasi antarpemangku kepentingan dalam penataan ruang masih belum optimal.
10
Paul, Shounak, Pawan Goyal, and Saptarshi Ghosh. "LeSICiN: A Heterogeneous Graph-Based Approach for Automatic Legal Statute Identification from Indian Legal Documents." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 10 (June 28, 2022): 11139–46. http://dx.doi.org/10.1609/aaai.v36i10.21363.
Full textAbstract:
The task of Legal Statute Identification (LSI) aims to identify the legal statutes that are relevant to a given description of facts or evidence of a legal case. Existing methods only utilize the textual content of facts and legal articles to guide such a task. However, the citation network among case documents and legal statutes is a rich source of additional information, which is not considered by existing models. In this work, we take the first step towards utilising both the text and the legal citation network for the LSI task. We curate a large novel dataset for this task, including facts of cases from several major Indian Courts of Law, and statutes from the Indian Penal Code (IPC). Modeling the statutes and training documents as a heterogeneous graph, our proposed model LeSICiN can learn rich textual and graphical features, and can also tune itself to correlate these features. Thereafter, the model can be used to inductively predict links between test documents (new nodes whose graphical features are not available to the model) and statutes (existing nodes). Extensive experiments on the dataset show that our model comfortably outperforms several state-of-the-art baselines, by exploiting the graphical structure along with textual features.
11
Deakin, Simon, Zoe Adams, Parisa Bastani, and Louise Bishop. "The CBR-LRI Dataset: Methods, Properties and Potential of Leximetric Coding of Labour Laws." International Journal of Comparative Labour Law and Industrial Relations 33, Issue 1 (February 1, 2017): 59–91. http://dx.doi.org/10.54648/ijcl2017004.
Full textAbstract:
Leximetric data coding techniques aim to measure cross-national and inter-temporal variations in the content of legal rules, thereby facilitating statistical analysis of legal systems and their social and economic impacts. In this article we explain how leximetric methods were used to create the CBR Labour Regulation Index (CBR-LRI), an index and related dataset of labour laws from around the world spanning the period from 1970 to 2013. Datasets of this kind must, we suggest, observe certain conventions of transparency and validity if they are to be usable in statistical analysis. The theoretical framework informing the construction of the dataset and the types of questions which it is are designed to answer should be made explicit. Then the choices involved in the selection of indicators, the definition of coding algorithms, and the aggregation and weighting of data to create composite measures, must be spelled out. In addition, primary legal sources should be referenced, and it should be clear how they were used to generate reported values. With these points in mind we provide an overview of the CBR-LRI dataset’s main features and structure, discuss issues of weighting, and present some initial findings on what it reveals of global trends in labour regulation.
12
Chen, Zhe, Hongli Zhang, Lin Ye, and Shang Li. "An Approach Based on Multilevel Convolution for Sentence-Level Element Extraction of Legal Text." Wireless Communications and Mobile Computing 2021 (December 24, 2021): 1–12. http://dx.doi.org/10.1155/2021/1043872.
Full textAbstract:
In the judicial field, with the increase of legal text data, the extraction of legal text elements plays a more and more important role. In this paper, we propose a sentence-level model of legal text element extraction based on the structure of multilabel text classification. Our proposed model contains an encoder and an improved decoder. The encoder applies multilevel convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) as feature extraction networks to extract local neighborhood and context information from legal text, and a decoder applies LSTM with multiattention and full connection layer with an improved initialization method to decode and generate label sequences. To our best knowledge, it is one of the first attempts to apply a multilabel classification algorithm for element extraction of legal text. In order to verify the effectiveness of our model, we conduct experiments not only on three real legal text datasets but also on a general multilabel text classification dataset.The experimental results demonstrate that our proposed model outperforms baseline models on legal text datasets, and our model is competitive to baseline models on the general text multilabel classification dataset, which indicates that our proposed model is useful for multilabel classification tasks of ordinary texts and legal texts with an uncertain number of characters in words and short lengths.
13
Munshi, Amr Abdullah, Wesam Hasan AlSabban, Abdullah Tarek Farag, Omar Essam Rakha, Ahmad Al Sallab, and Majid Alotaibi. "Automated Islamic Jurisprudential Legal Opinions Generation Using Artificial Intelligence." Pertanika Journal of Science and Technology 30, no. 2 (March 14, 2022): 1135–56. http://dx.doi.org/10.47836/pjst.30.2.16.
Full textAbstract:
Islam is the second-largest and fastest-growing religion. The Islamic Law, Sharia, represents a profound component of the day-to-day lives of Muslims. While sources of Sharia are available for anyone, it often requires a highly qualified person, the Mufti, to provide Fatwa. With Islam followers representing almost 25% of the planet earth population, generating many queries, and the sophistication of the Mufti qualification process, creating a shortage in them, we have a supply-demand problem, calling for Automation solutions. This scenario motivates the application of Artificial Intelligence (AI) to Automated Islamic Fatwa in a scalable way that can adapt to various sources like social media. In this work, the potential of AI, Machine Learning, and Deep Learning, with technologies like Natural Language Processing (NLP), paving the way to help the Automation of Islam Fatwa are explored. The work started by surveying the State-of-The-Art (SoTA) of NLP and exploring the potential use-cases to solve the problems of Question answering and Text Classification in the Islamic Fatwa Automation. The first and major enabler component for AI application for Islamic Fatwa, the data were presented by building the largest dataset for Islamic Fatwa, spanning the widely used websites for Fatwa. Moreover, the baseline systems for Topic Classification, Topic Modeling, and Retrieval-based Question-Answering are presented to set the future research and benchmark on the dataset. Finally, the dataset is released and baselines to the public domain to help advance future research in the area.
14
NURBAYEV, DANIYAR. "The rule of law, central bank independence and price stability." Journal of Institutional Economics 14, no. 4 (June 20, 2017): 659–87. http://dx.doi.org/10.1017/s1744137417000261.
Full textAbstract:
AbstractThis work empirically investigates the effect of the interaction between the rule of law and legal central bank independence (CBI) on price stability (the level of inflation and inflation volatility), employing a panel dataset that covers up to 124 countries over the period from 1970 to 2013. A new, largely complete legal CBI dataset, covering 182 countries was used for the work. The results indicate that the effect of legal CBI on price stability depends on the strength of the rule of law. Moreover, the results reveal that legal CBI has no significant effect on price stability when the rule of law is weak. The findings also show that 67% of advanced countries possess a rule of law that is strong enough to maintain price stability by increasing central bank autonomy, while only 4.5% of developing countries possess it.
15
Shankar, Atreya, Andreas Waldis, Christof Bless, Maria Andueza Rodriguez, and Luca Mazzola. "PrivacyGLUE: A Benchmark Dataset for General Language Understanding in Privacy Policies." Applied Sciences 13, no. 6 (March 14, 2023): 3701. http://dx.doi.org/10.3390/app13063701.
Full textAbstract:
Benchmarks for general language understanding have been rapidly developing in recent years of NLP research, particularly because of their utility in choosing strong-performing models for practical downstream applications. While benchmarks have been proposed in the legal language domain, virtually no such benchmarks exist for privacy policies despite their increasing importance in modern digital life. This could be explained by privacy policies falling under the legal language domain, but we find evidence to the contrary that motivates a separate benchmark for privacy policies. Consequently, we propose PrivacyGLUE as the first comprehensive benchmark of relevant and high-quality privacy tasks for measuring general language understanding in the privacy language domain. Furthermore, we release performances from multiple transformer language models and perform model–pair agreement analysis to detect tasks where models benefited from domain specialization. Our findings show the importance of in-domain pretraining for privacy policies. We believe PrivacyGLUE can accelerate NLP research and improve general language understanding for humans and AI algorithms in the privacy language domain, thus supporting the adoption and acceptance rates of solutions based on it.
16
Kemala, Ade Putera, and Hafizh Ash Shiddiqi. "Analysis of Indonesian Language Dataset for Tax Court Cases: Multiclass Classification of Court Verdicts." Jurnal Riset Informatika 5, no. 3 (June 10, 2023): 419–24. http://dx.doi.org/10.34288/jri.v5i3.555.
Full textAbstract:
Tax is an obligation that arises due to the existence of laws, creating a duty for citizens to contribute a certain portion of their income to the state. The Tax Court serves as a judicial authority for taxpayers seeking justice in tax disputes, handling various types of taxes daily. This paper analyzes an Indonesian language dataset of tax court cases, aiming to perform multiclass classification to predict court verdicts. The dataset undergoes preprocessing steps, while data augmentation using oversampling and label weighting techniques addresses class imbalance. Two models, bi-LSTM and IndoBERT, are utilized for classification. The research produced a final result of the model with 75.83% using the IndoBERT model. The results demonstrate the efficacy of both models in predicting court verdicts. This research has implications for predicting court conclusions with limited case details, providing valuable insights for legal decision-making processes. The findings contribute to legal data analysis, showcasing the potential of NLP techniques in understanding and predicting court outcomes, thus enhancing the efficiency of legal proceedings.
17
Morris, Katherine, and Anita Arzoomanian. "Insights from Regulatory Data on Development Needs of Community Pharmacy Professionals." Pharmacy 8, no. 3 (July 7, 2020): 111. http://dx.doi.org/10.3390/pharmacy8030111.
Full textAbstract:
The aim of this study was to use data available to a Canadian health professions regulator (Ontario College of Pharmacists) to identify areas of opportunity where practitioners (pharmacists and pharmacy technicians) could benefit from further development, in order to optimize practice and improve the quality of care. Four de-identified datasets were used to extract themes from areas of jurisprudence (1969 exam records), member practice assessments (2610 records), pharmacy assessments (2024 records) and conduct (640 case records). Outcome measures included performance in examinations and assessments and competency gaps identified in conduct investigations. Thematic analysis of outcomes was done in two stages. First, the four outcomes were derived independently for each dataset. Second, the top five issues were extracted for each dataset. It was hypothesized that common themes in competency gaps across all four datasets would emerge from this top five selection. We found three main common areas of opportunity where practitioners could benefit from further development: patient assessment and safety; documentation; and ethical, legal and professional responsibilities.
18
Lonardo, Luigi, and Andrea Palazzi. "A Dataset, Software Toolbox, and Interdisciplinary Research Agenda for the Common Foreign and Security Policy." European Foreign Affairs Review 25, Issue 2 (August 1, 2020): 281–96. http://dx.doi.org/10.54648/eerr2020023.
Full textAbstract:
The article introduces a text corpus containing all the legal acts adopted by the European Union from 1 December 2009 till 30 June 2019; it also provides an open-source built-for-purpose software toolbox that can be used to re-create and manipulate the dataset. The dataset, as well as the software toolbox, are publicly available on GitHub at: https://github.com/ndrplz/eurlextoolbox. The article describes the content and possible uses of the dataset and maps out some potential applications thereof. Since EU law plays a key role in virtually all aspects of European integration, we believe that the dataset, by making the legal dimension easily accessible, could be of interest to an interdisciplinary audience. Building on previous literature on text-as-data approaches and qualitative methods applied to EU law, we make the case for an interdisciplinary agenda, and then illustrate it through research questions in a distinctive area of EU foreign affairs: the Common Foreign and Security Policy (CFSP). European Union Law, European Union Law Database, Research Methodology, Data analysis, Text-as-Data, Corpus Analysis, Common Foreign and Security Policy
19
Carlotti, Danilo. "TEXT SUMMARIZATION AS AN EMPIRICAL LEGAL RESEARCH TOOL." Revista de Estudos Empíricos em Direito 10 (November 25, 2022): 1–17. http://dx.doi.org/10.19092/reed.v10.600.
Full textAbstract:
This paper use text summarization techniques as a tool for empirical legal research, creating a summary of the decisions given the phrases predictive power with regards to the decision outcome. A dataset of habeas corpus decisions from various courts in Brazil is used that explicitly cite the COVID pandemic as a reason for requesting the release of the patients. A predictive model is created and through this analysis we propose to find the arguments most correlated with the outcome.
20
Rice, Douglas, Jesse H. Rhodes, and Tatishe Nteta. "Racial bias in legal language." Research & Politics 6, no. 2 (April 2019): 205316801984893. http://dx.doi.org/10.1177/2053168019848930.
Full textAbstract:
Although racial bias in the law is widely recognized, it remains unclear how these biases are in entrenched in the language of the law, judicial opinions. In this article, we build on recent research introducing an approach to measuring the presence of implicit racial bias in large-scale corpora. Utilizing an original dataset of more than one million appellate court opinions from US state and federal courts, we estimate word embeddings for the more than 400,000 most common words found in legal opinions. In a series of analyses, we find strong and consistent evidence of implicit racial bias, as African-American names are more frequently associated with unpleasant or negative concepts, whereas European-American names are more frequently associated with pleasant or positive concepts. The results have stark implications for work on the neutrality of the legal system as well as for our understanding of the entrenchment of bias through the law.
21
Mosaher, Quazi Saad-ul, and Mousumi Hasan. "Offline Handwritten Signature Recognition Using Deep Convolution Neural Network." European Journal of Engineering and Technology Research 7, no. 4 (August 29, 2022): 44–47. http://dx.doi.org/10.24018/ejeng.2022.7.4.2851.
Full textAbstract:
In the modern age, technological advancement reached a new limit where authentication plays a vital role in security management. Biometric-based authentication is the most referenced procedure for authentication where signature verification is a significant part of it for authentication of a person. To prevent the falsification of signatures on important documents & legal transactions it is necessary to recognize a person's signature accurately. This paper focused on recognizing offline handwritten original & forged signatures using a deep convolution neural network. We use a completely new dataset & also downloaded datasets to train the system & verify a random signature as genuine or forgery. All testing samples are collected from several individuals after several steps of preprocessing the model is fed with the resultant image to our system, the experimental results give us an accuracy of 95.5% from the dataset.
22
Pandey, Radhika, Rajeswari Sengupta, Aatmin Shah, and Bhargavi Zaveri. "Legal restrictions on foreign institutional investors in a large, emerging economy: A comprehensive dataset." Data in Brief 28 (February 2020): 104819. http://dx.doi.org/10.1016/j.dib.2019.104819.
Full text
23
Buschmann, Andy. "Introducing the Myanmar Protest Event Dataset Motivation, Methodology, and Research Prospects." Journal of Current Southeast Asian Affairs 37, no. 2 (August 2018): 125–42. http://dx.doi.org/10.1177/186810341803700205.
Full textAbstract:
This article presents the Myanmar Protest Event Dataset, a unique dataset on protest assemblies in transitional Myanmar/Burma. The data contents were derived from the most visible forms of assembly – demonstrations, protest marches and labour strikes – and collected through a protest event analysis of local news reports. The coded variables range from information on the actual moment of the protest event, such as participants, issue, duration and location, to the aftermath, including variables related to legal consequences for protesters and the success of protesters’ claims, and many others. Besides a concise description of the research design and data collection process, this article discusses methodological strengths and weaknesses of the dataset.
24
Sarretta, A., and M. Minghini. "TOWARDS THE INTEGRATION OF AUTHORITATIVE AND OPENSTREETMAP GEOSPATIAL DATASETS IN SUPPORT OF THE EUROPEAN STRATEGY FOR DATA." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVI-4/W2-2021 (August 19, 2021): 159–66. http://dx.doi.org/10.5194/isprs-archives-xlvi-4-w2-2021-159-2021.
Full textAbstract:
Abstract. Digital transformation is at core of Europe’s future and the importance of data is well highlighted by the recently published European strategy for data, which envisions the establishment of so-called European data spaces enabling seamless data flows across actors and sectors to ultimately boost the economy and generate innovation. Integrating datasets produced by multiple actors, including citizen-generated data, is a key objective of the strategy. This study focuses on OpenStreetMap (OSM), the most popular crowdsourced geographic information project, and is the first step towards an exploration of pros and cons of integrating its open-licensed data with authoritative geospatial datasets from European National Mapping Agencies. In contrast to previous work, which has only tested data integration at the local or regional level, an experiment was presented to integrate the national address dataset published by the National Land Survey (NLS) of Finland with the corresponding dataset from OSM. The process included the analysis of the two datasets, a mapping between their data models and a set of processing steps – performed using the open source QGIS software – to transform and finally combine their content. The resulting dataset confirms that, while addresses from the NLS are in general more complete across Finland, in some areas OSM addresses provide a higher detail and more up-to-date information to usefully complement the authoritative one. Whilst the analysis confirms that an integration between OSM and authoritative geospatial datasets is technically and semantically feasible, future work is needed to evaluate enablers and barriers that also exist at the legal and organisational level.
25
Koniaris, Marios, Dimitris Galanis, Eugenia Giannini, and Panayiotis Tsanakas. "Evaluation of Automatic Legal Text Summarization Techniques for Greek Case Law." Information 14, no. 4 (April 21, 2023): 250. http://dx.doi.org/10.3390/info14040250.
Full textAbstract:
The increasing amount of legal information available online is overwhelming for both citizens and legal professionals, making it difficult and time-consuming to find relevant information and keep up with the latest legal developments. Automatic text summarization techniques can be highly beneficial as they save time, reduce costs, and lessen the cognitive load of legal professionals. However, applying these techniques to legal documents poses several challenges due to the complexity of legal documents and the lack of needed resources, especially in linguistically under-resourced languages, such as the Greek language. In this paper, we address automatic summarization of Greek legal documents. A major challenge in this area is the lack of suitable datasets in the Greek language. In response, we developed a new metadata-rich dataset consisting of selected judgments from the Supreme Civil and Criminal Court of Greece, alongside their reference summaries and category tags, tailored for the purpose of automated legal document summarization. We also adopted several state-of-the-art methods for abstractive and extractive summarization and conducted a comprehensive evaluation of the methods using both human and automatic metrics. Our results: (i) revealed that, while extractive methods exhibit average performance, abstractive methods generate moderately fluent and coherent text, but they tend to receive low scores in relevance and consistency metrics; (ii) indicated the need for metrics that capture better a legal document summary’s coherence, relevance, and consistency; (iii) demonstrated that fine-tuning BERT models on a specific upstream task can significantly improve the model’s performance.
26
Yang, Liu. "Study on Storage and Query System of Legal Documents." Applied Mechanics and Materials 533 (February 2014): 452–55. http://dx.doi.org/10.4028/www.scientific.net/amm.533.452.
Full textAbstract:
There is a logically centralized level global data centers to meet the global schema database for centralized storage needs. This will not only ensure efficient query dataset brings advantages, without compromising the autonomy of each data source. Logically centralized layer needs to have at least a central database, data dump module. This paper studies storage and query system of legal documents based on the information integration system and its implementation methods, the application can be completed more intelligent reasoning queries.
27
Haw, In-Mu G., Simon S. M. Ho, Yuansha Li, and Feida (Frank) Zhang. "Product Market Competition, Legal Institutions, and Accounting Conservatism." Journal of International Accounting Research 14, no. 2 (February 1, 2015): 1–39. http://dx.doi.org/10.2308/jiar-51051.
Full textAbstract:
ABSTRACT In this study, we examine product market competition's role in shaping accounting conservatism in an international setting. Using a large dataset from 38 countries, we find evidence that product market competition is positively associated with accounting conservatism in countries with strong legal institutions, but not in countries with weak legal institutions. Moreover, the positive association is significantly more pronounced in countries with high-quality financial reporting environments comprising a higher earnings quality, more frequent and greater disclosure practices, and the more stringent enforcement of insider trading regulations. Our empirical findings suggest that product market competition and strong legal institutions jointly drive accounting conservatism.
28
Licht, Amanda A. "Introducing Regular Turnover Details, 1960–2015: A dataset on world leaders’ legal removal from office." Journal of Peace Research 59, no. 2 (November 17, 2021): 277–85. http://dx.doi.org/10.1177/00223433211045854.
Full textAbstract:
The premier data on leader survival focus on the violent, dramatic means by which leaders ‘exit’ office. This information, vital for many research questions, constitutes a valuable public good for the community. Yet, it provides an incomplete picture of the political rise and fall of world leaders. The burgeoning study of leaders using survival analysis requires a fine-grained understanding of not just when, but why and how leaders lose power. We cannot, for example, conclude that a leader’s exit implies a successful application of international pressure if her removal stems from pre-set constitutional laws and the immediate successor has long been considered the heir apparent. The Regular Turnover Details dataset remedies this problem. Two principal variables report information about the manner of each leader’s exit and the relationship between outgoing and incoming leaders, allowing analysts to arbitrate between exits that suggest political failure and those that don’t, identify non-political leaders (such as interim and technocratic executives), and determine whether leaders constitute heirs to power or challengers thereto.
29
Guerriero, Carmine. "A novel dataset on legal traditions, their determinants, and their economic role in 155 transplants." Data in Brief 8 (September 2016): 394–98. http://dx.doi.org/10.1016/j.dib.2016.05.049.
Full text
30
Benzmüller, Christoph, Ali Farjami, David Fuenmayor, Paul Meder, Xavier Parent, Alexander Steen, Leendert van der Torre, and Valeria Zahoransky. "LogiKEy workbench: Deontic logics, logic combinations and expressive ethical and legal reasoning (Isabelle/HOL dataset)." Data in Brief 33 (December 2020): 106409. http://dx.doi.org/10.1016/j.dib.2020.106409.
Full text
31
Yao, Feng, Jingyuan Zhang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Yun Liu, and Weixing Shen. "Unsupervised Legal Evidence Retrieval via Contrastive Learning with Approximate Aggregated Positive." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 4 (June 26, 2023): 4783–91. http://dx.doi.org/10.1609/aaai.v37i4.25603.
Full textAbstract:
Verifying the facts alleged by the prosecutors before the trial requires the judges to retrieve evidence within the massive materials accompanied. Existing Legal AI applications often assume the facts are already determined and fail to notice the difficulty of reconstructing them. To build a practical Legal AI application and free the judges from the manually searching work, we introduce the task of Legal Evidence Retrieval, which aims at automatically retrieving the precise fact-related verbal evidence within a single case. We formulate the task in a dense retrieval paradigm, and jointly learn the constrastive representations and alignments between facts and evidence. To get rid of the tedious annotations, we construct an approximated positive vector for a given fact by aggregating a set of evidence from the same case. An entropy-based denoise technique is further applied to mitigate the impact of false positive samples. We train our models on tens of thousands of unlabeled cases and evaluate them on a labeled dataset containing 919 cases and 4,336 queries. Experimental results indicate that our approach is effective and outperforms other state-of-the-art representation and retrieval models. The dataset and code are available at https://github.com/yaof20/LER.
32
AlZahrani, Fetoun Mansour, and Maha Al-Yahya. "A Transformer-Based Approach to Authorship Attribution in Classical Arabic Texts." Applied Sciences 13, no. 12 (June 18, 2023): 7255. http://dx.doi.org/10.3390/app13127255.
Full textAbstract:
Authorship attribution (AA) is a field of natural language processing that aims to attribute text to its author. Although the literature includes several studies on Arabic AA in general, applying AA to classical Arabic texts has not gained similar attention. This study focuses on investigating recent Arabic pretrained transformer-based models in a rarely studied domain with limited research contributions: the domain of Islamic law. We adopt an experimental approach to investigate AA. Because no dataset has been designed specifically for this task, we design and build our own dataset using Islamic law digital resources. We conduct several experiments on fine-tuning four Arabic pretrained transformer-based models: AraBERT, AraELECTRA, ARBERT, and MARBERT. Results of the experiments indicate that for the task of attributing a given text to its author, ARBERT and AraELECTRA outperform the other models with an accuracy of 96%. We conclude that pretrained transformer models, specifically ARBERT and AraELECTRA, fine-tuned using the Islamic legal dataset, show significant results in applying AA to Islamic legal texts.
33
SIEMS, MATHIAS M. "Varieties of legal systems: towards a new global taxonomy." Journal of Institutional Economics 12, no. 3 (February 1, 2016): 579–602. http://dx.doi.org/10.1017/s1744137415000545.
Full textAbstract:
AbstractLegal scholars, economists and other social scientist often refer to the idea that countries can be classified into a number of ‘legal families’ or ‘legal origins’. Yet, this research is unsatisfactory as regards the actual classifications of the legal systems of the world. It is the aim of this paper to fill this gap and to develop a more robust taxonomy of legal systems. This taxonomy is based on a new dataset of 156 countries that is subsequently analysed with tools of network analysis. Applying cluster optimisation, this paper finds that the world's legal systems can be divided into four clusters. It displays those clusters in a map, akin to the Inglehart–Welzel cultural map. It is suggested that those findings have important implications, not only for our understanding of the legal world, but also for the feasibility of legal transplants and harmonisation.
34
Zhao, Peilian, Cunli Mao, and Zhengtao Yu. "Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding." International Journal of Asian Language Processing 30, no. 03 (September 2020): 2050012. http://dx.doi.org/10.1142/s2717554520500125.
Full textAbstract:
Aspect-Based Sentiment Analysis (ABSA), a fine-grained task of opinion mining, which aims to extract sentiment of specific target from text, is an important task in many real-world applications, especially in the legal field. Therefore, in this paper, we study the problem of limitation of labeled training data required and ignorance of in-domain knowledge representation for End-to-End Aspect-Based Sentiment Analysis (E2E-ABSA) in legal field. We proposed a new method under deep learning framework, named Semi-ETEKGs, which applied E2E framework using knowledge graph (KG) embedding in legal field after data augmentation (DA). Specifically, we pre-trained the BERT embedding and in-domain KG embedding for unlabeled data and labeled data with case elements after DA, and then we put two embeddings into the E2E framework to classify the polarity of target-entity. Finally, we built a case-related dataset based on a popular benchmark for ABSA to prove the efficiency of Semi-ETEKGs, and experiments on case-related dataset from microblog comments show that our proposed model outperforms the other compared methods significantly.
35
Seeja, K. R., and Masoumeh Zareapoor. "FraudMiner: A Novel Credit Card Fraud Detection Model Based on Frequent Itemset Mining." Scientific World Journal 2014 (2014): 1–10. http://dx.doi.org/10.1155/2014/252797.
Full textAbstract:
This paper proposes an intelligent credit card fraud detection model for detecting fraud from highly imbalanced and anonymous credit card transaction datasets. The class imbalance problem is handled by finding legal as well as fraud transaction patterns for each customer by usingfrequent itemset mining.A matching algorithm is also proposed to find to which pattern (legal or fraud) the incoming transaction of a particular customer is closer and a decision is made accordingly. In order to handle the anonymous nature of the data, no preference is given to any of the attributes and each attribute is considered equally for finding the patterns. The performance evaluation of the proposed model is done on UCSD Data Mining Contest 2009 Dataset (anonymous and imbalanced) and it is found that the proposed model has very high fraud detection rate, balanced classification rate, Matthews correlation coefficient, and very less false alarm rate than other state-of-the-art classifiers.
36
Stow, May Tamara, Chidiebere Ugwu, and Laeticia Onyejegbu. "An Improved Model for Legal Case Text Document Classification." European Journal of Electrical Engineering and Computer Science 7, no. 2 (April 26, 2023): 58–64. http://dx.doi.org/10.24018/ejece.2023.7.2.509.
Full textAbstract:
Misjudgments in court cases are inevitable in any judicial system irrespective of how civilized the country in which the judicial system is. The economic effects of failed court judgments cannot be overemphasized. The passing of wrong judgments can be a result of a lack of evidence due to poor research by counsels. Preparing for a court case is not an easy fit as a lot of research must be done on the part of the attorneys in charge. This paper presents an improved Hybrid model for legal case document classification. The system starts by collecting legal case documents from an online domain. The collected documents were converted to texts using a pdf miner library in python. The converted texts were used in creating tables using the pandas library. After the creation of the dataset table, the dataset was pre-processed by removing noise, and non-alphanumeric values, and performing tokenization. The tokenized data was then passed into principal component analysis for the selection of important features. The selected features were used in training an LSTM model for the classification of the legal case documents. The system was designed with Object-Oriented Analysis and Design method and implemented using python programming language. The result of the LSTM is outstanding, having an accuracy of 99% when evaluated with unseen legal case documents. The model was deployed in building a web application for the classification of legal documents. Upon testing the application with emerging documents, it sufficiently classified them and reduced tremendously the conflicting judgments experienced before the application of the improved model for legal case classification.
37
Samarawickrama, Chamodi, Melonie de Almeida, Nisansa de Silva, Gathika Ratnayaka, and Amal Shehan Perera. "Legal Party Extraction from Legal Opinion Texts Using Recurrent Deep Neural Networks." Journal of Data Intelligence 3, no. 3 (August 2022): 350–65. http://dx.doi.org/10.26421/jdi3.3-4.
Full textAbstract:
Since the advent of deep learning based Natural Language Processing (NLP), diverse domains of human society have benefited form automation and the resultant increment in efficiency. Law and order are, undoubtedly, crucial for the proper functioning of society; for without law there would be chaos, failing to offer equality to everyone. The legal domain being such a vital field, the incorporation of NLP into its workings has drawn attention in many research studies. This study attempts to leverage NLP into the task of extracting legal parties from legal opinion text documents. This task is of high importance given the significance of existing legal cases on contemporary cases under the legal practice, \textit{case law}. This study proposes a novel deep learning methodology which can be effectively used to resolve the problem of identifying legal party members in legal documents. We present two models here, where the first is a BRNN model to detect whether an entity is a legal party or not, and a second, a modification of the same neural network, to classify the thus identified entities into petitioner and defendant classes. Furthermore, in this study, we introduce a novel data set which is annotated with legal party information by an expert in the legal domain. With the use of the said dataset, we have trained and evaluated our models where the experiments carried out support satisfactory performance of our solution. The deep learning model we hereby propose, provides a benchmark for the legal party identification task on this data set. Evaluations for the solution presented in the paper show that our system has 90.89\% precision and 91.69\% recall for legal party extraction from an unseen paragraph from a legal document. As for the classification of petitioners and defendants, we show that GRU-512 obtains the highest F1 score.
38
Bonica, Adam, and Maya Sen. "A Common-Space Scaling of the American Judiciary and Legal Profession." Political Analysis 25, no. 1 (January 2017): 114–21. http://dx.doi.org/10.1017/pan.2016.10.
Full textAbstract:
We extend the scaling methodology previously used in Bonica (2014) to jointly scale the American federal judiciary and legal profession in a common space with other political actors. The end result is the first dataset of consistently measured ideological scores across all tiers of the federal judiciary and the legal profession, including 840 federal judges and 380,307 attorneys. To illustrate these measures, we present two examples involving the U.S. Supreme Court. These data open up significant areas of scholarly inquiry.
39
Tanvir, Kazi, Saidul Mursalin Khan, Al-Jobair Ibna Ataur, and Shaikh Allahma Galib. "Offline-Signature Verification System using Transfer Learning VGG-19." International Journal of Research In Science & Engineering, no. 25 (September 29, 2022): 30–37. http://dx.doi.org/10.55529/ijrise.25.30.37.
Full textAbstract:
Nowadays, Signature verification is one of the most common and effective biometric systems that used to recognize people in many institutions. In modern era of technology, advanced neural networks have provided us an option to solve this issue. In this study, The Robinreni Signature Dataset was utilized to classify the signatures of 64 people, each of whom had 64 original signatures and 64 fake signatures. One of the most popular CNN architecture, namely, VGG19, were used. Firstly, the dataset was distributed accordingly 1649 and 500 for training and validation. Secondly, preprocess the data to train the model. After that the model training process is started using transfer learning approach. Obtained experimental results that VGG19 is best suited for datasets with a validation accuracy of 98.79%.. Everyone has their own unique signature that used to identify and verify important documents and legal transactions. Our study shows the effectiveness of VGG19 for Signature Verification task. The findings will aid in the development of more effective Deep Learning-based signature verification methods.
40
Zhu, Kongfan, Rundong Guo, Weifeng Hu, Zeqiang Li, and Yujun Li. "Legal Judgment Prediction Based on Multiclass Information Fusion." Complexity 2020 (October 26, 2020): 1–12. http://dx.doi.org/10.1155/2020/3089189.
Full textAbstract:
Legal judgment prediction (LJP), as an effective and critical application in legal assistant systems, aims to determine the judgment results according to the information based on the fact determination. In real-world scenarios, to deal with the criminal cases, judges not only take advantage of the fact description, but also consider the external information, such as the basic information of defendant and the court view. However, most existing works take the fact description as the sole input for LJP and ignore the external information. We propose a Transformer-Hierarchical-Attention-Multi-Extra (THME) Network to make full use of the information based on the fact determination. We conduct experiments on a real-world large-scale dataset of criminal cases in the civil law system. Experimental results show that our method outperforms state-of-the-art LJP methods on all judgment prediction tasks.
41
Dove, John A. "Antitrust enforcement by state attorneys general: institutional, legal and political considerations." Business and Politics 16, no. 2 (August 2014): 291–312. http://dx.doi.org/10.1515/bap-2013-0032.
Full textAbstract:
Since deregulation in 1980, there has been a major shift in antitrust enforcement to the states, specifically to state attorneys general (AGs). For advocates of deregulation, this move has had important unintended consequences. Specifically, it has allowed antitrust litigation to become hitched to the political incentives of AGs. Analysis of a panel dataset of all state antitrust actions between 1990 and 2008 suggests that antitrust enforcement by state attorneys general appears to follow electoral cycles, which is especially pronounced depending on specific institutional constraints that exist between the states.
42
Haglund, Jillienne, and David L. Richards. "Enforcement of sexual violence law in post-civil conflict societies." Conflict Management and Peace Science 35, no. 3 (May 18, 2017): 280–95. http://dx.doi.org/10.1177/0738894217695536.
Full textAbstract:
The climate of impunity in many post-civil conflict societies results in unprecedented levels of violence against women, making legal implementation and law enforcement particularly difficult. We argue that the presence of strong legal provisions mediates the negative influence of the post-civil conflict environment on violence against women. Specifically, we examine the role of strong legal protections on the enforcement of sexual violence legislation in post-civil conflict countries. To examine our hypothesis, we utilize an original dataset measuring the strength and enforcement of domestic legal statutes addressing violence against women for the years 2007–2010 in post-civil conflict countries. We find elements of civil conflict as well as domestic and international legal regimes to be reliably associated with the enforcement of violence against women laws and rape prevalence in post-civil conflict states.
43
Zhang, Dian, Hewei Zhang, Long Wang, Jiamei Cui, and Wen Zheng. "Recognition of Chinese Legal Elements Based on Transfer Learning and Semantic Relevance." Wireless Communications and Mobile Computing 2022 (April 30, 2022): 1–11. http://dx.doi.org/10.1155/2022/1783260.
Full textAbstract:
In recent years, LegalAI has rapidly attracted the attention of AI researchers and legal professionals alike. Elements of LegalAI are known as legal elements. These elements can bring intermediate supervisory information to the judicial trial task and make the model’s prediction results more interpretable. This paper proposes a Chinese legal element identification method based on BERT’s contextual relationship capture mechanism to identify the elements by measuring the similarity between legal elements and case descriptions. On the China Law Research Cup 2019 Judicial Artificial Intelligence Challenge (CAIL-2019) dataset, the final result improves 4.2 points over the method based on the BERT model but without using similarity metrics. This research method makes full use of the semantic information of text, which is essential in the judicial field of document processing.
44
Tacea, Angela. "A New Research Agenda: How European Institutions Influence Law-Making in Justice and Home Affairs." Politics and Governance 9, no. 3 (July 30, 2021): 5–15. http://dx.doi.org/10.17645/pag.v9i3.4081.
Full textAbstract:
The article presents a dataset on the legislative procedure in European Justice and Home Affairs (JHA) and a new method of data processeing. The dataset contains information on 529 procedures proposed between January 1998 and December 2017. For each of the legislative proposals, the dataset identifies the main elements of the legislative procedure (e.g., dates, types of procedure, directory codes and subcodes, actors, voting results, amendments, legal basis, etc.) and the changes introduced at each step of the legislative process from the text proposed by the European Commission to the final version published in the <em>Official Journal of the European Union</em>. This information has been gathered using text mining techniques. The dataset is relevant for a broad range of research questions regarding the EU decision-making process in JHA related to the balance of powers between European institutional actors and their capacity to influence the legislative outputs.
45
Jung, Courtney, and Evan Rosevear. "Economic and Social Rights Across Time, Regions, and Legal Traditions: A Preliminary Analysis of the TIESR Dataset." Nordic Journal of Human Rights 30, no. 03 (December 19, 2012): 372–94. http://dx.doi.org/10.18261/issn1891-814x-2012-03-07.
Full text
46
Saveliev, Denis. "On Creating and Using Text of the Russian Federation Corpus of Legal Acts as an Open Dataset." Law. Journal of the Higher School of Economics, no. 1 (March 10, 2018): 26–44. http://dx.doi.org/10.17323/2072-8166.2018.1.26.44.
Full text
47
Bhat, Mohammad Idrees, and B. Sharada. "Automatic Recognition of Legal Amounts on Indian Bank Cheques." International Journal of Computer Vision and Image Processing 10, no. 4 (October 2020): 54–73. http://dx.doi.org/10.4018/ijcvip.2020100104.
Full textAbstract:
Holistic-based approaches attempt to represent an entire handwritten word as an indivisible entity by representing it with feature representations. Despite the presence of various feature representations, it still remains a challenge to get the effective representation for Devanagari Legal amounts. In this paper, an attempt is made to represent legal amounts with histogram of oriented gradients (HOG) and local binary patterns (LBP) for their characterization. Thereafter, two fusion-based models are proposed. In the first model, HOG and LBP are fused at feature level and, in second, at decision level. Later, recognition is performed with the nearest neighbor and support vector machine classifiers. For corroboration of the efficacy of the proposed models several experiments have been conducted on ICDAR ' 11 Devanagari Legal amount dataset. Experimental results demonstrate that fusion based approaches are effective by achieving significant improvement in recognition accuracy as compared to individual feature representations and other contemporary approaches employed on the data set.
48
Escobar-Linero, Elena, María García-Jiménez, María Eva Trigo-Sánchez, María Jesús Cala-Carrillo, José Luis Sevillano, and Manuel Domínguez-Morales. "Using machine learning-based systems to help predict disengagement from the legal proceedings by women victims of intimate partner violence in Spain." PLOS ONE 18, no. 6 (June 7, 2023): e0276032. http://dx.doi.org/10.1371/journal.pone.0276032.
Full textAbstract:
Intimate partner violence against women (IPVW) is a pressing social issue which poses a challenge in terms of prevention, legal action, and reporting the abuse once it has occurred. However, a significant number of female victims who file a complaint against their abuser and initiate legal proceedings, subsequently, withdraw charges for different reasons. Research in this field has been focusing on identifying the factors underlying women victims’ decision to disengage from the legal process to enable intervention before this occurs. Previous studies have applied statistical models to use input variables and make a prediction of withdrawal. However, none have used machine learning models to predict disengagement from legal proceedings in IPVW cases. This could represent a more accurate way of detecting these events. This study applied machine learning (ML) techniques to predict the decision of IPVW victims to withdraw from prosecution. Three different ML algorithms were optimized and tested with the original dataset to assess the performance of ML models against non-linear input data. Once the best models had been obtained, explainable artificial intelligence (xAI) techniques were applied to search for the most informative input features and reduce the original dataset to the most important variables. Finally, these results were compared to those obtained in the previous work that used statistical techniques, and the set of most informative parameters was combined with the variables of the previous study, showing that ML-based models had a better predictive accuracy in all cases and that by adding one new variable to the previous work’s predictive model, the accuracy to detect withdrawal improved by 7.5%.
49
Thapa, Chandra, Jun Wen Tang, Alsharif Abuadbba, Yansong Gao, Seyit Camtepe, Surya Nepal, Mahathir Almashor, and Yifeng Zheng. "Evaluation of Federated Learning in Phishing Email Detection." Sensors 23, no. 9 (April 27, 2023): 4346. http://dx.doi.org/10.3390/s23094346.
Full textAbstract:
The use of artificial intelligence (AI) to detect phishing emails is primarily dependent on large-scale centralized datasets, which has opened it up to a myriad of privacy, trust, and legal issues. Moreover, organizations have been loath to share emails, given the risk of leaking commercially sensitive information. Consequently, it has been difficult to obtain sufficient emails to train a global AI model efficiently. Accordingly, privacy-preserving distributed and collaborative machine learning, particularly federated learning (FL), is a desideratum. As it is already prevalent in the healthcare sector, questions remain regarding the effectiveness and efficacy of FL-based phishing detection within the context of multi-organization collaborations. To the best of our knowledge, the work herein was the first to investigate the use of FL in phishing email detection. This study focused on building upon a deep neural network model, particularly recurrent convolutional neural network (RNN) and bidirectional encoder representations from transformers (BERT), for phishing email detection. We analyzed the FL-entangled learning performance in various settings, including (i) a balanced and asymmetrical data distribution among organizations and (ii) scalability. Our results corroborated the comparable performance statistics of FL in phishing email detection to centralized learning for balanced datasets and low organizational counts. Moreover, we observed a variation in performance when increasing the organizational counts. For a fixed total email dataset, the global RNN-based model had a 1.8% accuracy decrease when the organizational counts were increased from 2 to 10. In contrast, BERT accuracy increased by 0.6% when increasing organizational counts from 2 to 5. However, if we increased the overall email dataset by introducing new organizations in the FL framework, the organizational level performance improved by achieving a faster convergence speed. In addition, FL suffered in its overall global model performance due to highly unstable outputs if the email dataset distribution was highly asymmetric.
50
Zhang, Hu, Bangze Pan, and Ru Li. "Legal Judgment Elements Extraction Approach with Law Article-aware Mechanism." ACM Transactions on Asian and Low-Resource Language Information Processing 21, no. 3 (May 31, 2022): 1–15. http://dx.doi.org/10.1145/3485244.
Full textAbstract:
Legal judgment elements extraction (LJEE) aims to identify the different judgment features from the fact description in legal documents automatically, which helps to improve the accuracy and interpretability of the judgment results. In real court rulings, judges usually need to scan both the fact descriptions and the law articles repeatedly to find out the relevant information, and it is hard to acquire the key judgment features quickly, so legal judgment elements extraction is a crucial and challenging task for legal judgment prediction. However, most existing methods follow the text classification framework, which fails to model the attentive relations of the law articles and the legal judgment elements. To address this issue, we simulate the working process of human judges, and propose a legal judgment elements extraction method with a law article-aware mechanism, which captures the complex semantic correlations of the law article and the legal judgment elements. Experimental results show that our proposed method achieves significant improvements than other state-of-the-art baselines on the element recognition task dataset. Compared with the BERT-CNN model, the proposed “All labels Law Articles Embedding Model (ALEM)” improves the accuracy, recall, and F1 value by 0.5, 1.4 and 1.0, respectively.