Search

Legal documents, like contracts or laws, are subject to interpretation. Different people can have different interpretations of the very same document. Large parts of judicial branches all over the world are concerned with settling disagreements that arise, in part, from these different interpretations. In this context, it only seems natural that during the annotation of legal machine learning data sets, disagreement, how to report it, and how to handle it should play an important role. This article presents an analysis of the current state-of-the-art in the annotation of legal machine learning data sets. The results of the analysis show that all of the analysed data sets remove all traces of disagreement, instead of trying to utilise the information that might be contained in conflicting annotations. Additionally, the publications introducing the data sets often do provide little information about the process that derives the "gold standard" from the initial annotations, often making it difficult to judge the reliability of the annotation process. Based on the state-of-the-art, the article provides easily implementable suggestions on how to improve the handling and reporting of disagreement in the annotation of legal machine learning data sets. [ABSTRACT FROM AUTHOR]

Despite the public availability of legal documents, there is a need for finding specific information contained in them, such as paragraphs, clauses, items and so on. With such support, users could find more specific information than only finding whole legal documents. Some research efforts have been made in this area, but there is still a lot to be done to have legal information available more easily to be found. Thus, due to the large number of published legal documents and the high degree of connectivity, simple access to the document is not enough. It is necessary to recover the related legal framework for a specific need. In other words, the retrieval of the set of legal documents and their parts related to a specific subject is necessary. Therefore, in this work, we present a proposal of a RDF-based graph to represent and search parts of legal documents, as the output of a set of terms that represents the pursued legal information. Such a proposal is well-grounded on an ontological view, which makes possible to describe the general structure of a legal system and the structure of legal documents, providing this way the grounds for the implementation of the proposed RDF graph in terms of the meaning of their parts and relationships. We posed several queries to retrieve parts of legal documents related to sets of words and the results were significant. [ABSTRACT FROM AUTHOR]

Access to legal information is fundamental to access to justice. Yet accessibility refers not only to making legal documents available to the public, but also rendering legal information comprehensible to them. A vexing problem in bringing legal information to the public is how to turn formal legal documents such as legislation and judgments, which are often highly technical, to easily navigable and comprehensible knowledge to those without legal education. In this study, we formulate a three-step approach for bringing legal knowledge to laypersons, tackling the issues of navigability and comprehensibility. First, we translate selected sections of the law into snippets (called CLIC-pages), each being a small piece of article that focuses on explaining certain technical legal concept in layperson's terms. Second, we construct a Legal Question Bank, which is a collection of legal questions whose answers can be found in the CLIC-pages. Third, we design an interactive CLIC Recommender. Given a user's verbal description of a legal situation that requires a legal solution, CRec interprets the user's input and shortlists questions from the question bank that are most likely relevant to the given legal situation and recommends their corresponding CLIC pages where relevant legal knowledge can be found. In this paper we focus on the technical aspects of creating an LQB. We show how large-scale pre-trained language models, such as GPT-3, can be used to generate legal questions. We compare machine-generated questions against human-composed questions and find that MGQs are more scalable, cost-effective, and more diversified, while HCQs are more precise. We also show a prototype of CRec and illustrate through an example how our 3-step approach effectively brings relevant legal knowledge to the public. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is rapidly expanding in myriad industries and systems. This study sought to investigate public trust in using AI in the criminal court process. While previous research has identified factors that influence trust in AI, such as perceived accuracy and transparency of algorithms, less is known about the role of influential leaders—such as judges—in shaping public trust in new technology. This study examined the relationship between locus of control, anthropomorphism, cultural values, and perceived trust in AI. Participants completed a survey assessing their perceptions of trust in AI in determining bail eligibility, bail fines and fees, sentencing length, sentencing fines and fees, and writing legal documents (e.g., findings and disposition). Participants were more likely to trust AI performing financial calculations rather than determining bail eligibility, sentence length, or drafting legal documents. Participants' comfort with AI in decision-making also depended on their perceptions of judges' trust in AI, and they expressed concerns about AI perpetuating bias and the need for extensive testing to ensure accuracy. Interestingly, no significant association was found with other participant characteristics (e.g., locus of control, anthropomorphism, or cultural values). This study contributes to the literature by highlighting the role of judges as influential leaders in shaping public trust in AI and examining the influence of individual differences on trust in AI. The findings also help inform the development of recommended practices and ethical guidelines for the responsible use of AI in the courts. [ABSTRACT FROM AUTHOR]

Legal text retrieval serves as a key component in a wide range of legal text processing tasks such as legal question answering, legal case entailment, and statute law retrieval. The performance of legal text retrieval depends, to a large extent, on the representation of text, both query and legal documents. Based on good representations, a legal text retrieval model can effectively match the query to its relevant documents. Because legal documents often contain long articles and only some parts are relevant to queries, it is quite a challenge for existing models to represent such documents. In this paper, we study the use of attentive neural network-based text representation for statute law document retrieval. We propose a general approach using deep neural networks with attention mechanisms. Based on it, we develop two hierarchical architectures with sparse attention to represent long sentences and articles, and we name them Attentive CNN and Paraformer. The methods are evaluated on datasets of different sizes and characteristics in English, Japanese, and Vietnamese. Experimental results show that: (i) Attentive neural methods substantially outperform non-neural methods in terms of retrieval performance across datasets and languages; (ii) Pretrained transformer-based models achieve better accuracy on small datasets at the cost of high computational complexity while lighter weight Attentive CNN achieves better accuracy on large datasets; and (iii) Our proposed Paraformer outperforms state-of-the-art methods on COLIEE dataset, achieving the highest recall and F2 scores in the top-N retrieval task. [ABSTRACT FROM AUTHOR]

Evidences are important proofs to support judicial trials. Automatically extracting evidences from judgement documents can be used to assess the trial quality and support "Intelligent Court". Current evidence extraction is primarily depended on sequence labelling models. Despite their success, they can only assign a label to a token, which is difficult to recognize nested evidence entities in judgment documents, where a token may belong to several evidences at the same time. In this paper, we present a novel evidence extraction architecture called ATT-MRC, in which extracting evidence entities is formalized as a question answer problem, where all evidence spans are screened out as possible correct answers. Furthermore, to address the data imbalance problem in the judgement documents, we revised the loss function and combined it with a data enhancement technique. Experimental results demonstrate that our model has better performance than related works in evidence extraction. [ABSTRACT FROM AUTHOR]

Summarization of legal case judgement documents is a practical and challenging problem, for which many summarization algorithms of different varieties have been tried. In this work, rather than developing yet another summarization algorithm, we investigate if intelligently ensembling (combining) the outputs of multiple (base) summarization algorithms can lead to better summaries of legal case judgements than any of the base algorithms. Using two datasets of case judgement documents from the Indian Supreme Court, one with extractive gold standard summaries and the other with abstractive gold standard summaries, we apply various ensembling techniques on summaries generated by a wide variety of summarization algorithms. The ensembling methods applied range from simple voting-based methods to ranking-based and graph-based ensembling methods. We show that many of our ensembling methods yield summaries that are better than the summaries produced by any of the individual base algorithms, in terms of ROUGE and METEOR scores. [ABSTRACT FROM AUTHOR]

The appropriate understanding and fast processing of lengthy legal documents are computationally challenging problems. Designing efficient automatic summarization techniques can potentially be the key to deal with such issues. Extractive summarization is one of the most popular approaches for forming summaries out of such lengthy documents, via the process of summary-relevant sentence selection. An efficient application of this approach involves appropriate scoring of sentences, which helps in the identification of more informative and essential sentences from the document. In this work, a novel sentence scoring approach DCESumm is proposed which consists of supervised sentence-level summary relevance prediction, as well as unsupervised clustering-based document-level score enhancement. Experimental results on two legal document summarization datasets, BillSum and Forum of Information Retrieval Evaluation (FIRE), reveal that the proposed approach can achieve significant improvements over the current state-of-the-art approaches. More specifically it achieves ROUGE metric F1-score improvements of (1−6)% and (6−12)% for the BillSum and FIRE test sets respectively. Such impressive summarization results suggest the usefulness of the proposed approach in finding the gist of a lengthy legal document, thereby providing crucial assistance to legal practitioners. [ABSTRACT FROM AUTHOR]

Day by day, the amount of online and offline text data is growing tremendously from various sources like legal documents, medical documents, news articles, etc. Manual text summarization of large documents is unfeasible and costly because it takes much time and requires more effort. As a consequence, various graph-based text summarization techniques have been designed which provide thoroughly and well-prepared summaries of documents. The problems issues that exist in these techniques are redundancy of data, loss of information and readability. To overcome these problems, we have proposed a textual graph-based extractive text summarization technique called TGETS, for extracting essential information from a single document. In the proposed approach, a graph's node is denoted as group of sentences in the document and an edge of the graph is represented as an association between two sentences. The summary generation is based on the sum of sentence weight and the average weight of the textual graph. The performance of proposed approach is evaluated on the BBC news articles dataset through the ROUGE-metric ( R 1 and R 2 ). The proposed approach in the range of 100-200 words length summary offers better scores of 19.88%, 38.76%, and 30.73% for R 1 under precision, recall and F 1 -score with respect to the existing PageRank (PR) method. Similarly, for R 2 , the proposed approach exceeds by 32%, 26.99%, and 29.01% for precision, recall, and F 1 -score with respect to existing PageRank (PR) method. [ABSTRACT FROM AUTHOR]

This study aims to identify artificial intelligence (AI) technologies that are applied in climate-smart agricultural practices and address ethical concerns of deploying those technologies from legal perspectives. As climate-smart agricultural AI, the study considers those AI-based technologies that are used for precision agriculture, monitoring peat lands, deforestation tracking, and improved forest management. The study utilized a systematic literature review approach to identify and analyze AI technologies employed in climate-smart agriculture and associated ethical and legal concerns. The study findings indicate several ethical concerns for deploying AI in climate-smart agricultural practices pertaining to data inaccuracy, other technical errors based on wrong recommendations or wrongful acts, data ownership and intellectual property issues, and economic issues resulting in digital division and privacy and security related issues. In this study, the ethical concerns were further examined based on criminal law, tort law, privacy and data protection law, and intellectual property law. In this regard, the study finds that the current tort law pattern is more suitable than the criminal law pattern to address some major ethical concerns, such as data inaccuracy and other technical errors based on wrong recommendations or wrongful acts. Finally, the study recommends that at the global level, all countries need to fill up the current gap of international law on climate-smart agriculture through agreeing on a standard set of legal provisions and enhancing collaboration in innovation and deployment of climate-smart agricultural AI. It further recommends that at the local level, countries need to adopt suitable regulations addressing multi-stakeholders' interests associated with the deployment of climate-smart agricultural AIs. [ABSTRACT FROM AUTHOR]

While major advances have been made over the past years in comparing citizenship laws globally, most measures remain restricted to the law-on-the-books. Knowledge about the implementation of these laws remains limited. This poses the question to what extent these measures correspond with the law as experienced by targeted populations. In order to overcome the implementation gap when comparing and measuring citizenship law globally, this paper addresses the question of how to gain a coherent understanding of implementation. Developing a comprehensive typology, the paper distinguishes three crucial elements of implementation: (1) the entry into force of legal provisions (capturing the applicable state of citizenship law), (2) the interpretation of law (the specific interpretation of legal provisions used by the authorities responsible for their execution), and (3) the application of law (executing legal provisions in practice by the authorities). Subsequently, the paper illustrates how this typology can be applied to the analysis of citizenship law implementation by a case study of dual citizenship acceptance, focusing on the renunciation requirement for naturalisation and dual citizenship treaties. The paper concludes by outlining directions for a comparative research agenda that better corresponds with the lived experience of citizenship laws. [ABSTRACT FROM AUTHOR]

In his testamentary letter to Auguste Chevalier, Évariste Galois states that, in modern terminology, the smallest simple group has order 60. No proof of this statement survives in his papers, and it has been suggested that a proof would have been impossible using the methods available at the time. We argue that this assertion is unduly pessimistic. Moreover, one fragmentary document, dismissed as a triviality and misunderstood, looks suspiciously like cryptic notes related to this result. We give an elementary proof of Galois's statement, explain why it is likely that he would have been aware of the methods involved, and discuss the potential relevance of the fragment. [ABSTRACT FROM AUTHOR]

In this paper, we present a method for introducing law students to the writing of legal documents. The method uses a machine-readable representation of the legal knowledge to support document assembly and to help the students to understand how the assembly is performed. The knowledge base consists of enacted legislation, document templates, and assembly instructions. We propose a system called LEDAS (LEgal Document Assembly System) for the interactive assembly of legal documents. It guides users through the assembly process and provides explanations of the interconnection between input data and claims stated in the document. The system acts as a platform for practicing drafting skills and has great potential as an education tool. It allows teachers to configure the system for the assembly of some particular type of legal document and then enables students to draft the documents by investigating which information is relevant for these documents and how the input data shape the final document. The generated legal document is complemented by a graphical representation of legal arguments expressed in the document. The system is based on existing legal standards to facilitate its introduction in the legal domain. Applicability of the system in the education of future lawyers is positively evaluated by the group of law students and their TA. [ABSTRACT FROM AUTHOR]

This study investigated challenges that Saudi undergraduate learners face in translating oil contracts from English into Arabic. The study used a quantitative approach of data collection. The sample of this study consisted of 18 Saudi undergraduate learners of transaction departments at some Saudi universities. To achieve the objectives of this study, a test was designed and administered. Additionally, the relevant theoretical framework of legal translation and features of oil contracts were analysed to pinpoint the problematic areas and the gaps. The results of the study indicated that undergraduate learners provided unacceptable translation based on lexical and textual features. On the other hand, they provided poor translation based on syntactic features. The study suggests some practical solutions to overcome the difficulties of legal texts for translators. [ABSTRACT FROM AUTHOR]

"Payment for ecosystem services" (PES) schemes have been introduced worldwide as an instrument to support the participation of multiple actors through an organizational arrangement. In Brazil, Minas Gerais State's Prosecution Office (MPMG—Ministério Público de Minas Gerais, in Portuguese) acted as a pioneer in channeling resources from Deferred Prosecution Agreements (TACs—Termo de Ajustamento de Conduta, in Portuguese) to financially enable a PES project's implementation. This is the first study to have analyzed the performance of the MPMG as a prominent actor in the institutional arrangement related to this project. The research mobilizes the notion of institutional design as proposed by Corbera, et al. (Ecol Econ 68:743–761, 2009), which establishes that, for the long-term viability of PES schemes, different institutional actors have fundamental roles to play, specially dedicated to the financial sustainability of the schemes. This research involved related documents' analysis and a state-of-the-art review of the origin and implementation of the Oásis Brumadinho project in the Brazilian State of Minas Gerais. An analysis of the institutional arrangement of the Oásis Brumadinho project showed that the role of the State's Prosecution Office was crucial in making the PES feasible in terms of transaction costs. Our reflections on alternatives to finance PES projects will be useful for future cases, especially the new legal provision of the National Policy on Payment for Environmental Services at the federal level. Overall, this study furthers our understanding of the role played by the State's Prosecution Office and sheds light on the possibility of using TAC resources as an economic alternative to enable the implementation of PES frameworks in other locations in Brazil. [ABSTRACT FROM AUTHOR]

Sociology of penal practice has not systematically investigated religion as a powerful cultural element in shaping the criminal justice system in the modern world. Therefore, this study sought to analyze the potential influence of religion on developing penal policies in Iran. The Islamic Revolution of Iran which occurred in 1978-79 led to a great penal revolution based on the Sharia criminal law. This study, therefore, explores such a great penal revolution through the Durkheimian analysis of religion using qualitative analysis of legal documents, reports, and past journals, seeking to discover the religious nature of punishments as rooted in Iranian society itself. Moreover, applying Durkheim's sociological approach to religion, the study attempts to unearth the reason behind the harsh policies adopted in this regard despite their failure in achieving their philosophical and criminological objectives. [ABSTRACT FROM AUTHOR]

The legal system of parentage is a mature rule in traditional civil law, encompassing the acknowledgment and denial of parent-child relationships. In China, the parentage legal system outlined in the Civil Code is a guiding provision that requires supplementary operational rules. The rule of parentage presumption, as a crucial component of the parentage legal system, serves as the premise and foundation of the entire parentage system. China's parentage presumption involves both legal and factual presumptions. To elucidate the legislative intent and objective expression of the legal provisions concerning parentage in the Civil Code, it is necessary to clarify the legal attributes, logic, and effects of parentage presumption. Based on this, deviations in legal application due to inconsistent interpretations by different judges should be identified and adjusted. There exist four challenges in the practical application of the parentage presumption rule within the Chinese judicial system. It is imperative for judges to possess a precise and consistent understanding of these challenges. Article 1073 of the Civil Code and judicial interpretations constitute a remedial mechanism for parentage presumption. However, for this article to yield the intended legal effects, detailed specifications are needed regarding the parties eligible to file denial lawsuits of legitimate children, the grounds for denial, and the statute of limitations. Additionally, the implied recognition system reflected in the legal provision should also be supplemented with unified and applicable regulations to ensure operability within China's legal system. Only with consistent legislative interpretations and applications can the consistency of legal application in parentage relationships be safeguarded, thereby upholding the authority of the Civil Code. [ABSTRACT FROM AUTHOR]

Human trafficking is a harmful, widespread and pressing issue that demands attention. However, the prevalence of such crimes may vary across different countries and time periods, which means that there may not be a universal solution to addressing them. In response to the recent public outcry sparked by the incident of the woman chained in Feng County, Xuzhou, this article provides a comprehensive review of China's legislative and judicial responses to crimes against women and children who are abducted and sold, as well as the corresponding governance effects and causes. This study examines whether the punishment for buying and trafficking women and children should be increased through criminal law amendments and whether the current public outrage calling for equal punishment for buyers and sellers is justified. To provide a rational response to these issues, the article reviews all relevant laws, regulations, judicial cases, and typical cases from 1979 to 2022. An analysis of the change in case processing over the years was conducted using MATLAB software with the baseline panel regression model, robustness checks, and mechanism tests. This study reveals a decline on human trafficking crimes in China, but four provinces (Yunnan, Henan, Shandong, and Fujian) have a higher incidence. The article offers a comprehensive analysis from both macro and micro perspectives. National macro factors such as economic development, social welfare policies, rural revitalization, and COVID-19 prevention contribute to the decline. From a micro perspective, local differences in these provinces are a significant reason for high incidence from a micro perspective. This article suggests that legal amendments to increase punishment would be ineffective. Instead, existing legal provisions should be applied, and decision-making rules from typical cases should be utilized. [ABSTRACT FROM AUTHOR]

Legal documents serve as valuable repositories of information pertaining to crimes, encompassing not only legal aspects but also relevant details about criminal behaviors. To date and the best of our knowledge, no studies in the field examine legal documents for crime understanding using an Artificial Intelligence (AI) approach. The present study aims to fill this research gap by identifying relevant information available in legal documents for crime prediction using Artificial Intelligence (AI). This innovative approach will be applied to the specific crime of Intimate Partner Femicide (IPF). A total of 491 legal documents related to lethal and non-lethal violence by male-to-female intimate partners were extracted from the Vlex legal database. The information included in these documents was analyzed using AI algorithms belonging to Bayesian, functions-based, instance-based, tree-based, and rule-based classifiers. The findings demonstrate that specific information from legal documents, such as past criminal behaviors, imposed sanctions, characteristics of violence severity and frequency, as well as the environment and situation in which this crime occurs, enable the correct detection of more than three-quarters of both lethal and non-lethal violence within male-to-female intimate partner relationships. The obtained knowledge is crucial for professionals who have access to legal documents, as it can help identify high-risk IPF cases and shape strategies for preventing crime. While this study focuses on IPF, this innovative approach has the potential to be extended to other types of crimes, making it applicable and beneficial in a broader context. [ABSTRACT FROM AUTHOR]

Answering questions related to the legal domain is a complex task, primarily due to the intricate nature and diverse range of legal document systems. Providing an accurate answer to a legal query typically necessitates specialized knowledge in the relevant domain, which makes this task more challenging, even for human experts. Question answering (QA) systems are designed to generate answers to questions asked in natural languages. QA uses natural language processing to understand questions and search through information to find relevant answers. At this time, there is a lack of surveys that discuss legal question answering. To address this problem, we provide a comprehensive survey that reviews 14 benchmark datasets for question-answering in the legal field as well as presents a comprehensive review of the state-of-the-art Legal Question Answering deep learning models. We cover the different architectures and techniques used in these studies and discuss the performance and limitations of these models. Moreover, we have established a public GitHub repository that contains a collection of resources, including the most recent articles related to Legal Question Answering, open datasets used in the surveyed studies, and the source code for implementing the reviewed deep learning models (The repository is available at: https://github.com/abdoelsayed2016/Legal-Question-Answering-Review). The key findings of our survey highlight the effectiveness of deep learning models in addressing the challenges of legal question answering and provide insights into their performance and limitations in the legal domain. [ABSTRACT FROM AUTHOR]

Rights and duties are essential features of legal documents. Machine learning algorithms have been increasingly applied to extract information from such texts. Currently, their main focus is on named entity recognition, sentiment analysis, and the classification of court cases to predict court outcome. In this paper it is argued that until the essential features of such texts are captured, their analysis can remain bottle-necked by the very technology being used to assess them. As such, the use of legal theory to identify the most pertinent dimensions of such texts is proposed. Specifically, the interest theory of rights, and the first-order Hohfeldian taxonomy of legal relations. These principal legal dimensions allow for a stratified representation of knowledge, making them ideal for the abstractions needed for machine learning. This study considers how such dimensions may be identified. To do so it implements a novel heuristic based in philosophy coupled with language models. Hohfeldian relations of 'rights-duties' vs. 'privileges-no-rights' are determined to be identifiable. Classification of each type of relation to accuracies of 92.5% is found using Sentence Bidirectional Encoder Representations from Transformers. Testing is carried out on religious discrimination policy texts in the United Kingdom. [ABSTRACT FROM AUTHOR]

The mapping and assessment of ecosystems and their services (MAES) is key to inform sustainable policy and decision-making at national and sub-national levels. Responding to the paucity of research in sub-Saharan Africa, we conduct a pilot study for Eritrea that aims to map and assess the temporal dynamics of key ecosystems and their services. We reviewed policy and legal documents, analyzed land cover changes and estimated the potential for ecosystem services supply through an expert-based matrix approach. Our results showed that from 2015 to 2019, the potential supply of the ecosystem services analyzed (e.g., crop provisioning, water supply and recreation) increased, with the exception of wood supply. Overall, our study presents policy-relevant insights as to where to conserve, develop, or restore ecosystem services supply in Eritrea. Our approach is transferable to similar data scarce contexts and can thereby support policies toward more sustainable land development for people and nature. [ABSTRACT FROM AUTHOR]

Community-based treatment has long been a major component of the criminal justice system in most Western jurisdictions; however, this is not the case in China. Based on a review of academic journal articles and legal documents, this paper highlights the evolution of community correction programs for juvenile offenders in China. Reflecting on its development over the past two decades, the existing community correction programs in China are not restorative in facilitating an offender's effective reintegration into the community. This paper aims to address the existing gap by examining the historical roots and characteristics of Chinese juvenile community corrections and analyzing how restorative justice can be incorporated into the youth rehabilitation system. In this regard, this paper advocates for a restorative juvenile community correction model that motivates social capital and actively engages all concerned parties in meeting various correctional goals of victim reparation, accountability taking, capacity building, and maintaining community safety. With the momentum of the recent criminal justice reform alongside the continued open-door policy in China, it is hoped that the Chinese government may be more willing to include restorative ideas for offender reintegration in the future. With more frequent applications of restorative justice, we are confident that effective intervention models could be put into practice in the years to come. [ABSTRACT FROM AUTHOR]

Automatic legal text summarization becomes a challenging process because of unusual structure and high complexity of the documents. Existing works related to legal text summarization are available, both for general text and a few targeted in summarizing legal documents, however, they relied on massive quantity of labelled dataset by the use of hand-engineered features, leveraging on domain knowledge and focused their attention on a narrow sub-domain for increased effectiveness. To resolve this issue, this paper presents an automated optimal DL based legal text summarization (ODL-LTS) approach. Initially, the proposed ODL-LTS technique performs similarity measurement using TF-IDF and Similarity based on Rouge-L scores (SROUGE). Besides, glowworm swarm optimization (GSO) with bidirectional gated recurrent neural network (BiGRNN) model is employed for summary generation, shows the novelty of the work. The major benefit of the ODL-LTS model is that it does not depend upon handcrafted features or domain specific knowledge, nor is their application limited to specific sub-domains thus making them suitable to be extended to other domains as well. The performance validation of the ODL-LTS technique takes place using our own dataset and the experimental results demonstrates the prosminig performance with the precision of 35.54%, recall of 51.60%, and F-score of 39.06%. [ABSTRACT FROM AUTHOR]

The purpose of this article is to assess the justness or unjustness of the securitization of Covid-19 in the Greek case. To do so, the Just Securitization Theory, is used as articulated by Rita Floyd to examine the following research question: Was there a just initiation and just conduct in the case of the securitization of Covid-19 in Greece? To answer this question, the methodology employed is a mix of methods proposed by Rita Floyd, such as the recourse to natural sciences to establish the actuality of the threat in combination with discourse analysis in political and scientific actors' speech acts and qualitative analysis of legal policy documents. In total, 85 statements and legal documents were examined for the period 26/02/2020 to 15/06/2020 which is considered to be the first "phase" of the pandemic. Overall, the analysis shows that the securitization of the Covid-19 pandemic in Greece was just. More specifically, there was indeed an existential threat, the securitizing actors were sincere in their intentions to securitize Covid-19, whereas the good gained from this securitization (physical survival and protection of public health) was greater than the harm inflicted (suspension of liberties). In addition, the results show that the securitization of Covid-19 in Greece did not cause more insecurity than it aimed to solve and that the overall response from the Greek Government was proportionate to the threat and respectful of the human rights of the people secured by the threat. [ABSTRACT FROM AUTHOR]

The task of rhetorical role labeling is to assign labels (such as Fact, Argument, Final Judgement, etc.) to sentences of a court case document. Rhetorical role labeling is an important problem in the field of Legal Analytics, since it can aid in various downstream tasks as well as enhances the readability of lengthy case documents. The task is challenging as case documents are highly various in structure and the rhetorical labels are often subjective. Previous works for automatic rhetorical role identification (i) mainly used Conditional Random Fields over manually handcrafted features, and (ii) focused on certain law domains only (e.g., Immigration cases, Rent law), and a particular jurisdiction/country (e.g., US, Canada, India). In this work, we improve upon the prior works on rhetorical role identification by proposing novel Deep Learning models for automatically identifying rhetorical roles, which substantially outperform the prior methods. Additionally, we show the effectiveness of the proposed models over documents from five different law domains, and from two different jurisdictions—the Supreme Court of India and the Supreme Court of the UK. Through extensive experiments over different variations of the Deep Learning models, including Transformer models based on BERT and LegalBERT, we show the robustness of the methods for the task. We also perform an extensive inter-annotator study and analyse the agreement of the predictions of the proposed model with the annotations by domain experts. We find that some rhetorical labels are inherently hard/subjective and both law experts and neural models frequently get confused in predicting them correctly. [ABSTRACT FROM AUTHOR]

Legal professionals in Malawi rely on a limited number of textbooks, outdated law reports and inadequate library services. Most documents available are in image form, are un-structured, i.e. contain no useful legal meta-data, summaries, keynotes, and do not support a system of citation that is essential to legal research. While advances in document processing and machine learning have benefited many fields, legal research is still only marginally affected. In this interdisciplinary research, the authors build semi-automatic tools for creating a corpus of Malawi criminal law decisions annotated with legal meta-data, case and law citations. We used this corpus to extract legal meta-data, including law and case citations as used in Malawi by employing machine learning tools, spaCy and Gensim LDA. We set the foundation for a new methodology for classifying Malawi criminal case law according to the recently introduced International Classification of Crime for Statistical Purposes (ICCS). [ABSTRACT FROM AUTHOR]

In this paper, we discuss previous research in automatic prediction of court decisions. We define the difference between outcome identification, outcome-based judgement categorisation and outcome forecasting, and review how various studies fall into these categories. We discuss how important it is to understand the legal data that one works with in order to determine which task can be performed. Finally, we reflect on the needs of the legal discipline regarding the analysis of court judgements. [ABSTRACT FROM AUTHOR]

The standard approach for abstractive text summarization is to use an encoder-decoder architecture. The encoder is responsible for capturing the general meaning from the source text, and the decoder is in charge of generating the final text summary. While this approach can compose summaries that resemble human writing, some may contain unrelated or unfaithful information. This problem is called "hallucination" and it represents a serious issue in legal texts as legal practitioners rely on these summaries when looking for precedents, used to support legal arguments. Another concern is that legal documents tend to be very long and may not be fed entirely to the encoder. We propose our method called LegalSumm for addressing these issues by creating different "views" over the source text, training summarization models to generate independent versions of summaries, and applying entailment module to judge how faithful these candidate summaries are with respect to the source text. We show that the proposed approach can select candidate summaries that improve ROUGE scores in all metrics evaluated. [ABSTRACT FROM AUTHOR]

Previous works mainly employ triple structural information in learning representations for knowledge graph, which results in poor performance of link prediction especially when it predicts new or few-fact entities. It is intuitive to introduce text information to supplement the missing semantic information for knowledge representation. However, existing methods only make alignment on the level of word or score function, and have not yet considered textual and structural information. Moreover, since the textual information is potentially redundant to represent the entities, how to extract relevant information and simultaneously alleviate the irrelevant information contained in the text is a challenging task. To tackle the above problems, this paper proposes a novel knowledge representation learning framework of joint semantic embedding using structural knowledge and entity description (JointSE). Firstly, we design a mutual attention mechanism to filter the effective information of fact triples and entity descriptions with respect to specific relationships. Secondly, we project the triples into the text semantic space using dot product to connect the triple with the relevant text description. In addition, we enhance triple-based entity representation and text-based entity representation using graph neural network to capture more useful graph structure information. Finally, extensive experiments on benchmark datasets and Chinese legal provisions dataset demonstrate that JointSE realizes the effective fusion of triple information, text semantic information, and graph structure information. We observe that JointSE is superior to previous methods in entity prediction and relationship prediction tasks. [ABSTRACT FROM AUTHOR]

Illuminated manuscripts are relatively well studied, but the available publications greatly focus on religious manuscripts of a geographically limited area. In contrast, technical examinations of illuminated legal documents have received far less attention, e.g., Spanish cartas ejecutorias de hidalguía (executory certificates of nobility). These documents are suitable case studies to deepen current knowledge of manuscript-making in Spain for two reasons: First, they are dated (late fifteenth to early eighteenth centuries); and second, they are unusual and understudied from both the textual and materials analysis standpoints. Cartas contain judicial proceedings whereby a family gained or was re-assigned hidalguía (lower nobility). A key exhibit to achieving this status was proving their "blood purity" which implied they were faithful Catholics, so finding religious representations within the document is common. In addition, families embedded their faith and links to monarchs in their coat of arms through symbols like crowned eagles, trees, and towers. The deliberate choice of heraldic and religious elements is as important as the materials used to produce them. Interested in better understanding illumination in Spain we are studying these unique documents from the historical, materials, and iconographic points of view. Herein, we present the earliest results of an ongoing survey, detailing two case studies: Davila and Nuñez D. Armesto cartas. This research uses a combination of: (a) instrumental techniques (X-ray fluorescence, reflectance, and infrared spectroscopies; peptide mass fingerprinting; and gas chromatography); and (b) historical research using both the manuscript's contents as primary sources, and published research. The preliminary results are enabling us to shed light onto Spanish (legal) illuminated manuscript-making, and the symbolic role materials played, e.g., use of precious metals adorning monarchical elements, presence of ultramarine mixed with azurite on both coats of arms, and on Virgin Mary's gown, etc. This survey intends to simultaneously learn more about illumination practices in Spain, inform conservation decisions, and hopefully better understand problems connected to historic ideologies that were legalized in beautiful albeit disturbing documents, e.g., persecution of non-Catholics at the time in Spain. [ABSTRACT FROM AUTHOR]

Precedence retrieval is the process of retrieving similar prior case documents for the given current case document in the legal domain. Referencing the prior cases is important to ensure that an identical situation is treated similarly in all the cases. Concise representation of case documents using catch phrases facilitates the practitioners to avoid spending more time on reading the whole documents for finding the prior cases. The existing approaches for precedent retrieval in the legal domain use either statistical or semantic similarity features to find the prior cases. However, the substruction similarity features that consider the context of the statement helps to correctly identify the prior cases. Further, the existing approaches consider the whole document while extracting the similarity features, which is time-consuming. In this paper, we propose to use a combination of statistical, semantic, and substruction similarity features that are extracted from the catch phrases of the legal documents. The catch phrases from legal documents are extracted by utilizing Sequence-to-Sequence deep neural network with stacked encoder-decoder and Long Short Term Memory (LSTM) as the recurrent unit. The substruction similarity features are obtained using a convolutional neural network. The IRLeD@FIRE-2017 dataset is used for evaluating our approach. The experimental results show that considering catch phrases reduces the retrieval time without reducing the retrieval performance. The k-paired t-test also shows that the improvement in performance of the model by using substruction similarity features that are extracted from the catch phrases is statistically significant when compared with other models. The PReLCaP outperforms state-of-the-art approaches with the MAP score of 0.632 on test data. [ABSTRACT FROM AUTHOR]

This exploratory study used semi-structured interviews with 90 U.S.-Mexico port-of-entry-crossers to investigate whether they or someone they know experienced gender-based misconduct while crossing. Results revealed U.S. Customs officers (1) asked for or gave travelers a phone number; and (2) made inappropriate comments or queries, such as suggestive comments and asking travelers' about their relationship status. Other experiences mentioned included unwanted touching and officers misusing private information obtained from travelers' legal documents to contact them on social media. Participants also described how fear of retaliation rendered them suitable targets for these behaviors. Finally, participants referenced capable guardianship by noting how the presence of family members influenced Customs officers' behavior. [ABSTRACT FROM AUTHOR]

The judiciarization of the psychiatric subject is a two-sided process. It could anti-discriminate people with mental illnesses but, at the same time, it could potentially provoke pathologization of mental illnesses. Current methodologies proposed to measure this important and complicated process for people with mental illnesses do not allow analysis on multiple levels (the macro, meso, and micro). In this article, to fill this gap we propose a methodological strategy that helps to investigate judiciarization of people with mental illnesses on multiple levels at once. This approach is based on critical discourse analysis of legal documents and court decisions that feature people with the poor mental health. Namely, we suggest how to measure the level or degree of judiciarization, its geographical evenness, actors in the legal process, its dimensions (the law branches of its occurrence), and linguistic content. We applied this methodology in examining 1,243 legal documents and 327,311 court decisions that were issued by agents of the Russian law system. The research findings show that judiciarization levels in Russia have been rising over the years, moving away from stigmatizing those with mental illnesses and towards anti-discrimination. Our paper could be of interest to socio-legal researchers and social policy practitioners. [ABSTRACT FROM AUTHOR]

The proper functioning of judicial and legislative institutions requires the efficient retrieval of legal documents from extensive datasets. Legal Information Retrieval focuses on investigating how to efficiently handle these datasets, enabling the retrieval of pertinent information from them. Relevance Feedback, an important aspect of Information Retrieval systems, utilizes the relevance information provided by the user to enhance document retrieval for a specific request. However, there is a lack of available corpora containing this information, particularly for the legislative scenario. Thus, this paper presents Ulysses-RFCorpus, a Relevance Feedback corpus for legislative information retrieval, built in the real-case scenario of the Brazilian Chamber of Deputies. To the best of our knowledge, this corpus is the first publicly available of its kind for the Brazilian Portuguese language. It is also the only corpus that contains feedback information for legislative documents, as the other corpora found in the literature primarily focus on judicial texts. We also used the corpus to evaluate the performance of the Brazilian Chamber of Deputies’ Information Retrieval system. Thereby, we highlighted the model’s strong performance and emphasized the dataset’s significance in the field of Legal Information Retrieval. [ABSTRACT FROM AUTHOR]

Legal issues of ICOs are significant in the contemporary financial world because this method of capital formation is becoming widespread. In spite of the significance of ICOs, there are no financial regulations in this field in the most important legal systems. Therefore, research concerning future legal provisions in the area of ICOs is needed. This paper concerns issues related to the scope and structure of future financial regulations applicable to ICOs. The author focuses on principles on which legal provisions in the field of ICOs should be based. National, European and international matters are discussed separately in this work. Matters regarding a future international organisation competent in issues of crypto-assets are elaborated. Furthermore, the author proposes to create a model convention on cryptocurrencies and bilateral agreements on the exchange of information in crypto-asset matters. Disclosure obligations, anti-manipulation provisions and anti-money laundering principles are also set out. Moreover, the author discusses issues regarding audit requirements, special methods of registration and innovative payment rules for crypto-asset purposes. Finally, recommendations concerning ICOs are made separately for national, European and international purposes. The author believes that the conclusions in this paper can be useful not only for legislators but also for international actors, European institutions and legal researchers. [ABSTRACT FROM AUTHOR]

Using data from a primary survey of 524 domestic workers in the cities of Ahmedabad and Kolkata, this paper critically assesses the status of domestic workers. It includes analyses of various characteristics of the domestic workspace such as employer–employee relationships, wages and working conditions, institutional supports, aspirations and collective bargaining keeping the legal provisions of social securities and other labour rights in India. The characteristics of informality include the absence of a written contract, social security, conventional bargaining method of wage determination, presence of multiple household employers, very little government intervention, distressed livelihood option and lack of decent work environment. The inferences drawn in this paper reinstate the abysmal status of domestic workers in India. Findings from the data from these two cities do validate the vulnerability of domestic work as an occupation and the lack of legislative protection. Despite few dissimilarities, the basic findings are in conformity with the primary characteristics of domestic work in India. [ABSTRACT FROM AUTHOR]

Introduction: This study employs sentiment analysis (SA) to examine the semantic structures of restrictive and protective abortion bills enacted in 2019. SA is a Natural Language Processing (NLP) technique that uses automation to extract affective indicators (emotive language) from text data. Assessing these indicators can help identify whether legal texts are framed, or intentionally biased in their wording. Identifying framing is important for understanding potentially biased interpretations of these laws. Methods: We identified a sample of 2019 abortion bills using the legislative tracking tool Legiscan and included those that met specified criteria (N = 19 bills). We categorized each bill as restrictive (n = 12) or protective (n = 7). We ran aggregate (i.e., all bills) and separate (protective × restrictive) SA, generating scores that we interpreted qualitatively (higher scores indicated predominance of positive wording). Results: In the aggregate analysis, 56% of text comprised negative terms (44% positive). Restrictive bills contained more negative language than protective bills (67% vs 58%). Although SA scores varied from −222 to +13, two laws scored 0, indicating neutrality. For comparison, the US Constitution's score equaled 1. Conclusion: Our findings confirm SA is useful to examine legal documents for language biases. The abortion bills we assessed seem framed along political ideologies, although the sample provided evidence that neutral wording is possible. Policy Implications: With the recent additions of conservative-leaning Justices to the US Supreme Court, Roe v. Wade is again at the center of partisan conflict. Thus, how abortion laws are framed draws further implications for how they may be interpreted when challenged in the court system. [ABSTRACT FROM AUTHOR]

Legal professionals strongly demand an automatic and convenient legal document recommendation system (LDRS) to identify similar judgments for preparing the advantageous and strategic arguments in the Court. Doc2Vec excellently learns semantically rich embedding (i.e., vector) space from the textual information of judgment corpus. During Doc2Vec learning, the practice of prior domain-specific knowledge can potentially enhance the embedding representation. This research thus proposes a pre-learned word embedding based LDRS (P-LDRS) that learns the Doc2Vec embedding using Legal domain-specific pre-learned word embedding possessing the Legal semantic knowledge. However, learning the judgment embedding from existing substantial Legal documents turns out to be a scalability issue for Doc2Vec. The proposed P-LDRS also provides additional functionality to learn the judgment embedding distributedly over the cluster of computing nodes using frameworks like MapReduce and Spark to address the scalability issue. The empirical analysis is performed with a non-distributed and a distributed variant of the proposed P-LDRS to validate the effectiveness and scalability. Experiment results showcase that proposed non-distributed P-LDRS perform significantly better than traditional Doc2Vec based LDRS with an Accuracy of 0.88, F1-Score of 0.82 and MCC Score of 0.73. They also demonstrate that the proposed distributed P-LDRS improves the time efficiency and achieves stable Accuracy of ≈ 0.88, F1-Score of ≈ 0.83 and MCC Score of ≈ 0.72, with an increasing number of nodes. [ABSTRACT FROM AUTHOR]

Document falsification is among the fastest growing problems all over the world. Disclosure of such document is not always possible due to the conspiracy of attorney bodies; especially legal documents such as bank cheques, contracts, cash memos, and so on. Handwritten document tampering detection due to addition of new word(s) in judicial documents is the prime objective of this research. Minute alteration in writing causes financial loss to a person or to an organization and decreases the global economy. Such intangible assets remain undiscovered owing to lack of proper forensic techniques. Though writing style imitation can be possible, however, the possibility of getting exactly the same pen of the authorized document is quite impossible for an imitator. Hence, the paper introduces a solution to detect forgery in handwritten legal documents by analyzing perceptually similar pen ink. Forgery activity happens either ends of a written document by appending new word(s)/letter(s) with similar type of pen. The work is formulated as a binary classification problem and established with the help of several statistical features and three different classifiers: Multilayer Perceptron(MLP), RBF-SVM, and Random Forest(RF). Besides, the problem has also been implemented through some DCNN approaches to check whether it is possible to reflect the forgery by direct approaches. The efficiency of the proposed method is quite promising for involvement in the examination of forensic documents. [ABSTRACT FROM AUTHOR]

EuroVoc is a thesaurus maintained by the European Union Publication Office, used to describe and index legislative documents. The EuroVoc concepts are organized following a hierarchical structure, with 21 domains, 127 micro-thesauri terms, and more than 6,700 detailed descriptors. The large number of concepts in the EuroVoc thesaurus makes the manual classification of legal documents highly costly. In order to facilitate this classification work, we present two main contributions. The first one is the development of a hierarchical deep learning model to address the classification of legal documents according to the EuroVoc thesaurus. Instead of training a classifier for each hierarchy level, our model allows the simultaneous prediction of the three levels of the EuroVoc thesaurus. Our second contribution concerns the proposal of a new legal corpus for evaluating the classification of documents written in Portuguese. This corpus, named EUR-Lex PT, contains more than 220k documents, labeled under the three EuroVoc hierarchical levels. Comparative experiments with other state-of-the-art models indicate that our approach has competitive results, at the same time offering the ability to interpret predictions through attention weights. [ABSTRACT FROM AUTHOR]

The focus in this Finland-based study is on violence in close relationships—a term that partly overlaps with the more commonly used 'domestic violence', 'family violence' and 'intimate partner violence'. We demonstrate how police officers' conceptualisations of such violence differ from how it is defined in relevant legal documents. The data consists of the Government Bill and legal text on the subject issued as part of a legal reform enacted in 2010, and of a qualitative sample of freelist responses from 79 police officers. We examined both sets of data using theory-driven directed content analysis and deriving from prevailing theoretical frameworks reflecting the family- and gender-based perspectives on violence. The results expose the predominance of a narrow definition of 'family' in police understandings of close relationships, but also a notably broad spectrum of conceptualisations of both physical and non-physical forms of violence. In contrast, the legal definition of a close relationship is broader and encompasses multiple types of relationships, whereas forms of violence are more strictly defined. These findings could explain some of the discrepancies between legal policies on violence in close relationships and police responses to it. [ABSTRACT FROM AUTHOR]

This paper provides an analysis of Australia's legal provisions and policies regarding truancy. We examine how low frequency truants feature in Australia's truancy law and policy and highlight similarities and differences in the cultural–legal context between Australian states and territories. Similarities include requirements to attend school from about six to 17 years of age and the legal culpability of (predominantly) the parents for children's non-attendance. Differences include little consistency in the threshold at which schools in different Australian states and territories are required to intervene once truancy has been identified and disparities in prosecutions and fines. We conclude that harmonising truancy laws in Australia is likely to increase parental understanding and thereby compliance with school attendance laws. [ABSTRACT FROM AUTHOR]

The European Union is working towards harmonizing legislation across Europe, in order to improve cross-border interchange of legal information. This goal is supported for instance via standards such as the European Law Identifier (ELI) and the European Case Law Identifier (ECLI), which provide technical specifications for Web identifiers and suggestions for vocabularies to be used to describe metadata pertaining to legal documents in a machine readable format. Notably, these ECLI and ELI metadata standards adhere to the RDF data format which forms the basis of Linked Data, and therefore have the potential to form a basis for a pan-European legal Knowledge Graph. Unfortunately, to date said specifications have only been partially adopted by EU member states. In this paper we describe a methodology to transform the existing legal information system used in Austria to such a legal knowledge graph covering different steps from modeling national specific aspects, to population, and finally the integration of legal data from other countries through linked data. We demonstrate the usefulness of this approach by exemplifying practical use cases from legal information search, which are not possible in an automated fashion so far. [ABSTRACT FROM AUTHOR]

The empirical link between governance and illegal logging is widely accepted amongst scientist, although a minority still purports that illegal logging does not necessarily prevail because of poor governance. However, the nexus linking governance, illegal logging and carbon emission is not well enshrined in scientific literature. This paper seeks to review the literature on illegal logging and governance and empirically investigate the effect of illegal logging and governance effectiveness on carbon emission. Using panel dynamic ordinary least square method on data covering three Congo Basin timber-producing countries and three Asian timber-producing countries, this paper further investigates disaggregated effects between these two groups of countries. The empirical evidence underscores that Congo Basin timber-producing countries are characterised by increasing trend of illegal logging, poor governance effectiveness and corruption. Panel regression reveals a positive and significant impact of illegal logging, governance effectiveness and corruption on carbon emission. Asian producing countries depict a reducing trend in illegal logging and improvements in governance and corruption. There is a positive but not significant impact of illegal logging on carbon emission, and governance effectiveness reduces carbon emission. Thus, the dynamics of governance, illegal logging and carbon emission is not the same between timber-producing countries in Asia and Congo producing counties, thus suggesting the ability of institutions to curb illegal logging and enforce laws to reduce the effects of carbon emission. Multi-stakeholder consultations, government engagement, partnerships and training of control staff can help curb corruption. Legality checks should go beyond having legal documents to effectively check and control of timber concessions and small-scale logging. [ABSTRACT FROM AUTHOR]

In the domain of legal information retrieval, an important challenge is to compute similarity between two legal documents. Precedents (statements from prior cases) play an important role in The Common Law system, where lawyers need to frequently refer to relevant prior cases. Measuring document similarity is one of the most crucial aspects of any document retrieval system which decides the speed, scalability and accuracy of the system. Text-based and network-based methods for computing similarity among case reports have already been proposed in prior works but not without a few pitfalls. Since legal citation networks are generally highly disconnected, network based metrics are not suited for them. Till date, only a few text-based and predominant embedding based methods have been employed, for instance, TF-IDF based approaches, Word2Vec (Mikolov et al. 2013) and Doc2Vec (Le and Mikolov 2014) based approaches. We investigate the performance of 56 different methodologies for computing textual similarity across court case statements when applied on a dataset of Indian Supreme Court Cases. Among the 56 different methods, thirty are adaptations of existing methods and twenty-six are our proposed methods. The methods studied include models such as BERT (Devlin et al. 2018) and Law2Vec (Ilias 2019). It is observed that the more traditional methods (such as the TF-IDF and LDA) that rely on a bag-of-words representation performs better than the more advanced context-aware methods (like BERT and Law2Vec) for computing document-level similarity. Finally we nominate, via empirical validation, five of our best performing methods as appropriate for measuring similarity between case reports. Among these five, two are adaptations of existing methods and the other three are our proposed methods. [ABSTRACT FROM AUTHOR]

The radiology report in a case of suspected child abuse is both a medical and a legal document. Such reports should be thorough, specific, well-constructed and without error. Structured templates and standardized reporting contribute to completeness, consistency and communication. Here, the authors discuss common reporting errors. Radiologists should be prepared that the radiology report in a case of suspected child abuse is likely to be used in court. [ABSTRACT FROM AUTHOR]

This paper concerns an information extraction process for building a dynamic legislation network from legal documents. Unlike supervised learning approaches which require additional calculations, the idea here is to apply information extraction methodologies by identifying distinct expressions in legal text in order to extract network information. The study highlights the importance of data accuracy in network analysis and improves approximate string matching techniques to produce reliable network data-sets with more than 98% precision and recall. The applications and the complexity of the created dynamic legislation network are also discussed and challenged. [ABSTRACT FROM AUTHOR]

Basic elements of the law, such as statuses and regulations, are embodied in natural language, and strictly depend on linguistic expressions. Hence, analyzing legal contents is a challenging task, and the legal domain is increasingly looking for automatic-processing support. This paper focuses on a specific context in the legal domain, which has so far remained unexplored: automatic processing of garnishment documents. A garnishment is a legal procedure by which a creditor can collect what a debtor owes by requiring to confiscate a debtor's property (e.g., a checking account) that is hold by a third party, dubbed garnishee. Our proposal, motivated by a real-world use case, is a versatile natural-language-processing pipeline to support a garnishee in the processing of a large-scale flow of garnishment documents. In particular, we mainly focus on two tasks: (i) categorize received garnishment notices onto a predefined taxonomy of categories; (ii) perform an information-extraction phase, which consists in automatically identifying from the text various information, such as identity of involved actors, amounts, and dates. The main contribution of this work is to describe challenges, design, implementation, and performance of the core modules and methods behind our solution. Our proposal is a noteworthy example of how data-science techniques can be successfully applied to a novel yet challenging real-world context. [ABSTRACT FROM AUTHOR]

This study is dedicated to 2 texts written by French Jesuit father Joseph-François Lafitau (1681–1746), created in the context of his missionary stay in Nouvelle France: Mémoire concernant la précieuse plante du gin-seng de Tartarie (1718) and Mœrs des Sauvages amériquains comparées aux mœrs des premiers temps (1724). Both texts permit a multi-level analysis of material dimensions of culture and knowledge in the history of knowledge, the first dealing with a botanical subject, the second an anthropological one. They convey a meta-reflective discourse on material-specific epistemological problems that is realized through narrative textual structures. These texts enable a structural view point of systemic functions of the materiality of knowledge in historical epistemological orders. Finally, they show exemplary and significant transmedia representation techniques and the associated textualization and visualization strategies. [ABSTRACT FROM AUTHOR]