Legal Judgments Research Articles

An Approach Based on Cross-Attention Mechanism and Label-Enhancement Algorithm for Legal Judgment Prediction

Legal Judgment Prediction aims to automatically predict judgment outcomes based on descriptions of legal cases and established law articles, and has received increasing attention. In the preliminary work, several problems still have not been adequately solved. One is how to utilize limited but valuable label information. Existing methods mostly ignore the gap between the description of established articles and cases, but directly integrate them. Second, most studies ignore the mutual constraint among the subtasks, such as logically or semantically, each charge is only related to some specific articles. To address these issues, we first construct a crime similarity graph and then perform a distillation operation to collect discriminate keywords for each charge. Furthermore, we fuse these discriminative keywords instead of established article descriptions into case embedding with a cross-attention mechanism to obtain deep semantic representations of cases incorporating label information. Finally, under a constraint among subtasks, we optimize the one-hot representation of ground-truth labels to guarantee consistent results across the subtasks based on the label-enhancement algorithm. To verify the effectiveness and robustness of our framework, we conduct extensive experiments on two public datasets. The experimental results show that the proposed method outperforms the state-of-art models by 3.89%/7.92% and 1.23%/2.50% in the average MF1-score of the subtasks on CAIL-Small/Big, respectively.

Katyń before the “népbíróságok”: How the Hungarian people’s courts suppressed the truth on the massacre of Polish officers

As the judicial practice of the Hungarian people’s courts (népbíróságok) in matters related to Katyń remains relatively unknown, this article’s objective is to address this area of historical (as well as legal) research. It focuses on demonstrating general outlines of the problem by a detailed analysis of some of the most notable cases against Hungarian major war criminals. It seeks to explain the role these proceedings played within the the policy of obliterating the memory of Katyń and why the members of pre-war ruling elite were charged on the grounds of their activities concerning the Katyń massacre. Furthermore, this article attempts to demonstrate in what way these accusations were important in proceedings against major Hungarian war criminals. What was the legal basis invoked whenever the defendants were accused of Katyń-related issues? How did the People’s Courts handle these charges? And finally, what (if any) was the eventual role of the Soviets in the proceedings? As the matter under examination lies at the crossroads of history and law (as legal judgments that mentioned Katyń in their content are the center of the analysis), the methodology used compiles the process traditionally used in historical research with standard legal interpretation tools. Combining both methods while analyzing the object through the lens of the judiciary perspective, this article places the outcomes of the examined legal proceedings in a broader historical context that allows noticing the legacies produced by People’s Courts sealing the Soviet lies in mid 1940s. This article posits that during proceedings and in judgments, Katyń was only discussed at the margins of primary considerations. Besides, at the current stage of scientific development, there’s a lack of evidence that the Soviets exerted any pressures on the Hungarian judiciary, at least in the aspects concerning matters related to Katyń. Neither were they interested in using Hungarian judiciary channels to pursue their own specific Katyń-related goals, still less to use them as a tribune to minimize their failure in attributing the responsibility for this crime to the Nazis in Nuremberg. It seems, therefore, that Katyń-related cases before the népbíróságok were solely intra-domestically oriented, and their goals never went beyond one of the instruments of obliterating the memory of Katyń within Hungarian society. Still, they produced some concrete social effects nonetheless. Firstly, as the criminal prosecutions were just only one of the plethora of instruments set in motion to eradicate the memory about Katyń in Hungary, their deterrent or dissuasive effect (especially during the Stalinist era) should not be underestimated. Secondly, by placing Katyń within the context of the antisemitic crimes for which some of the defendants were sentenced to death, the legacy left by the People’s Courts dramatically complicated the decoupling process of the Soviet murder of Polish officers from the rest of Nazi/Arrow Cross propaganda. This confusion makes the Katyń tragedy a hostage of the discussion on the People’s Court’s role as such. Finally, as the analysis below is limited to some most notable cases of Hungarian major war criminals, this article plays only an indicatory role. Therefore, setting aside these conclusions, one should not forget that many additional questions (e.g. the total number of people sentenced or otherwise punished for “Katyń propaganda,” comparative approaches with similar processes in other East-Central European states) still beg further research.

Contrastive Learning for Legal Judgment Prediction

Legal judgment prediction (LJP) is a fundamental task of legal artificial intelligence. It aims to automatically predict the judgment results of legal cases. Three typical subtasks are relevant law article prediction, charge prediction, and term-of-penalty prediction. Due to the wide range of potential applications, LJP has attracted a great deal of interest, prompting the development of numerous approaches. These methods mainly focus on building a more accurate representation of a case’s fact description in order to improve the performance of judgment prediction. They overlook, however, the practical judicial scenario in which human judges often compare similar law articles or possible charges before making a final decision. To this end, we propose a supervised contrastive learning framework for the LJP task. Specifically, we train the model to distinguish (1) various law articles within the same chapter of a Law and (2) similar charges of the same law article or related law articles. By this means, the fine-grained differences between similar articles/charges can be captured, which are important for making a judgment. Besides, we optimize our model by identifying cases with the same article/charge labels, allowing it to more effectively model the relationship between the case’s fact description and its associated labels. By jointly learning the LJP task with the aforementioned contrastive learning tasks, our model achieves better performance than the state-of-the-art models on two real-world datasets.

Multi-view overlapping clustering for the identification of the subject matter of legal judgments

The legal field is generally burdened by paper-heavy activities, and the management of massive amounts of legal judgments without the adoption of computational tools may compromise the effectiveness and efficiency of administration processes. In this paper, we propose MOSTA, a novel unsupervised method to support the automated identification of groups of legal judgments with similar characteristics, with the goal of reducing the manual effort necessary for the management of legal judgments.Methodologically, MOSTA learns two different embedding models for legal judgments. The first aims to represent the semantics of the textual content, while the second aims to represent co-citations of legal acts, also considering the granularity of the citations. Such representations are then fused through a multi-view approach based on an autoencoder, and the obtained representation is finally exploited by a novel overlapping clustering algorithm. The latter is an additional strong point of MOSTA, since, contrary to existing approaches, does not rely on additional input parameters that inherently influence the degree of overlap of the resulting clusters.Our experiments, performed on three textual datasets, including a real-world legal dataset provided by EUR-Lex, proved that the proposed representation of cited legal acts, the adopted multi-view fusion strategy, and the novel overlapping clustering algorithm implemented in MOSTA provide a positive contribution to the quality of the identified clusters. Finally, MOSTA demonstrated to be able to outperform by a great margin existing complete solutions based on fine-tuned BERT embedding models and existing overlapping clustering algorithms.

An experimental look at reasonable suspicion and police discretion

PurposeThis study aims to demonstrate the need for further examination of legal judgments and the exercise of discretion in policing.Design/methodology/approachA factorial vignette survey with traffic stop scenarios based on US Court of Appeals decisions was administered to 396 police officers across six states. Officers were asked to indicate their assessment of the presence of reasonable suspicion and the likelihood that they would extend the stop for investigatory purposes.FindingsOfficers' reasonable suspicion judgments are significantly influenced by the vignette facts and align with court ruling expectations. However, even in the presence of reasonable suspicion, responses indicate a limited use of officer discretion to extend the stop.Originality/valueAnalyses of officer decision-making often rely on large datasets with easy indicators of location, officer demographics and citizen demographics, but rarely consider the facts of individual cases. This study suggests more experimental research is needed to consider the impact of case facts on officer judgments and discretionary activity.

The Death Penalty in Barbados: Reforming a Colonial Legacy

This article explores the death penalty in Barbados. Drawing on the historical context and the punishment’s colonial origins, we seek to make sense of its more recent history, particularly a 2018 landmark legal judgment that has finally forced reform of the sanction in Barbados. The article explores the bifurcated penological history of the death penalty; while laws enacted in London were extended to colonial nations such as Barbados, suggesting a continuation of norms, the tools of criminal justice were wielded for different purposes in the metropole compared with the periphery. We consider the trajectory of this colonial imposition and the retention of repressive punishments after independence, the Caribbean resistance to international abolitionist pressure from the 1990s and the recent reform. The role of the death penalty as a political and symbolic tool is examined, considering especially the colonial legacy of capital punishment in Barbados and the extent to which this factor has shaped contemporary public debates on punishment.

The First Step in Resolving Medical Disputes Involving Physicians of South Korea: Fair Medical Appraisal

Physicians of South Korea are not guaranteed their safe health care environment amid the recent increase in medical disputes and changed medical disputes. There has been surprisingly high tendency of criminal punishment on physicians compared to foreign countries such as Japan, England and German. This criminal punishment has caused several problems such as avoidance treatment and defensive treatments, increasing medical costs, a phenomenon of avoiding applying to specialized department with a high risk of medical accidents. Considering the direct impact of medical appraisal on legal judgement, the medical community’s urgent task is to raise physicians who can conduct fair, objective and consistent medical appraisal of medical accidents.

A two-staged NLP-based framework for assessing the sentiments on Indian supreme court judgments.

Topic modeling is a powerful technique for uncovering hidden patterns in large documents. It can identify themes that are highly connected and lead to a certain region while accounting for temporal and spatial complexity. In addition, sentiment analysis can determine the sentiments of media articles on various issues. This study proposes a two-stage natural language processing-based model that utilizes Latent Dirichlet Allocation to identify critical topics related to each type of legal case or judgment and the Valence Aware Dictionary Sentiment Reasoner algorithm to assess people's sentiments on those topics. By applying these strategies, this research aims to influence public perception of controversial legal issues. This study is the first of its kind to use topic modeling and sentiment analysis on Indian legal documents and paves the way for a better understanding of legal documents.

조세불복사건 판단에 있어 인지 편향과 극복방안

Humans acquired heuristics for survival. Heuristics are mental shortcuts that save time by simplifying complex decisions into simple rules of thumb. Heuristics are useful in everyday life because they enable us to automatically make quick decisions with little effort. However, when making important decisions and legal judgments, heuristics can be dangerous. Before filing a lawsuit in an appeals proceeding against a taxation, it must be needed to file an administrative appeal. It is the procedure enforced by law. Administrative hearings is similar to the judicial proceedings. The evaluating of the weight of proof depends on the committee members just as the judge. The problem is that the judge could make wrong decision due to his or her cognitive bias. In the United States, many experimental studies have been conducted on jurors and judges to see if various heuristics actually occur. It is important for parties to accept the legal decision, so that the legal decision must not be biased.
 The purpose of this research is to analyze the cases that had been shown heuristics in administrative trial decisions and to research on debiasing. This paper analyzes decisions in which representativeness heuristics, hindsight bias, and confirmation bias appeared. In order to debiase, there are several trials like the cognitive correction(thinking the opposite etc.), environmental correction(reducing cognitive losses etc.), and systemic correction(decision support systems etc.).

Regression applied to legal judgments to predict compensation for immaterial damage.

Immaterial damage compensation is a controversial matter in the judicial practice of several law systems. Due to a lack of criteria for its assessment, the judge is free to establish the value based on his/her conviction. Our research motivation is that knowing the estimated amount of immaterial damage compensation at the initial stage of a lawsuit can encourage an agreement between the parties. We thus investigate text regression techniques to predict the compensation value from legal judgments in which consumers had problems with airlines and claim for immaterial damage. We start from a simple pipeline and create others by adding some natural language processing (NLP) and machine learning (ML) techniques, which we call adjustments. The adjustments include N-Grams Extraction, Feature Selection, Overfitting Avoidance, Cross-Validation and Outliers Removal. An special adjustment, Addition of Attributes Extracted by the Legal Expert (AELE), is proposed as a complementary input to the case text. We evaluate the impact of adding these adjustments in the pipeline in terms of prediction quality and execution time. N-Grams Extraction and Addition of AELE have the biggest impact on the prediction quality. In terms of execution time, Feature Selection and Overfitting Avoidance have significant importance. Moreover, we notice the existence of pipelines with subsets of adjustments that achieved better prediction quality than a pipeline with them all. The result is promising since the prediction error of the best pipeline is acceptable in the legal environment. Consequently, the predictions will likely be helpful in a legal environment.

Entangled Impurities in Contemporary Sindh: Some Evidence from Law and Bureaucracy

Abstract This article lays out a framework for conceptualizing how religious differences and hierarchical, hereditary inequality consolidate in contemporary Sindh. I argue that the terms Hindu, Dalit, and hari are often conflated due to their entangled trajectories. Addressing this conflation sheds light on how structural inequality and discrimination function in Sindh. The article begins by focusing on a government document that limits potential applicants for a sanitation job to “non-Muslims.” Next, it explores how the religious category of Hindu has become, over time, susceptible to ritual stigmas, social marginalization, caste oppression, and hierarchization. Last, it addresses a legal judgment that hinges on recognizing caste inequality but cannot say so. Analysis of the decision reveals how the entanglement of Hindu, Dalit, and hari legal categories produces certain citizen-subjects as perpetual legal minors requiring the state’s paternalistic protection. Throughout, the article illustrates how the production of multiple hierarchies in the social fabric of Sindh and Pakistan broadly operates through the deployment of caste stigma as a public secret.

A Robust Deep Model for Improved Categorization of Legal Documents for Predictive Analytics

Predictive legal analytics is a technology used to predict the chances of successful and unsuccessful outcomes in a particular case. Predictive legal analytics is performed through automated document classification for facilitating legal experts in their classification of court documents to retrieve and understand the details of specific legal factors from legal judgments for accurate document analysis. However, extracting these factors from legal texts document is a time-consuming process. In order to facilitate the task of classifying documents, a robust method namely Distributed Stochastic Keyword Extraction based Ensemble Theil-Sen Regressive Deep Belief Reweight Boost Classification (DSKE-TRDBRBC) is proposed. The DSKE-TRDBRBC technique consists of two major processes namely Keyword Extraction and Classification. At first, the t-distributed stochastic neighbor embedding technique is applied to DSKE-TRDBRBC for keyword extraction. This in turn minimizes the time consumption for document classification. After that, the Ensemble Theil-Sen Regressive Deep Belief Reweight Boosting technique is applied for document classification. The Ensemble boosting algorithm initially constructs’ set of Theil-Sen Regressive Deep Belief neural networks to classify the input legal documents. Then the results of the Deep Belief neural network are combined to built a strong classifier by reducing the error. This aids in improving the classification accuracy. The proposed method is experimentally evaluated with various metrics such as F-measure , recall, accuracy, precision, , and computational time. The experimental results quantitatively confirm that the proposed DSKE-TRDBRBC technique achieves better accuracy with lowest computation time as compared to the conventional approaches.

A High-Precision Two-Stage Legal Judgment Summarization

Legal judgments are generally very long, and relevant information is often scattered throughout the text. To complete a legal judgment summarization, capturing important, relevant information comprehensively from a lengthy text is crucial. The existing abstractive-summarization models based on pre-trained language have restrictions on the length of an input text. Another concern is that the generated summaries have not been well integrated with the legal judgment’s technical terms and specific topics. In this paper, we used raw legal judgments as information of different granularities and proposed a two-stage text-summarization model to handle different granularities of information. Specifically, we treated the legal judgments as a sequence of sentences and selected key sentence sets from the full texts as an input corpus for summary generation. In addition, we extracted keywords related to technical terms and specific topics in the legal texts and introduced them into the summary-generation model as an attention mechanism. The experimental results on the CAIL2020 and the LCRD datasets showed that our model achieved an overall 0.19–0.41 improvement in its ROUGE score, as compared to the baseline models. Further analysis also showed that our method could comprehensively capture essential and relevant information from lengthy legal texts and generate better legal judgment summaries.

Ensemble methods for improving extractive summarization of legal case judgements

Ensemble methods for improving extractive summarization of legal case judgements

Potential Legal Risk During Crisis: A Case Study on A Private Hospital in Malaysia

This is a case study on bomb threat and evacuation process at KPJ Seremban Specialist Hospital (KPJSSH) in Negeri Sembilan, Malaysia. This study identifies potential legal risks arising from bomb threat and evacuation process in a private hospital. Bomb threat is a crisis situation that need to be managed by the hospital. Bomb threat and the evacuation process can create legal liabilities to the hospital. To identify the potential legal risks, in‐depth content analysis was conducted on KPJSSH incident report, HICS guideline and legal judgment obtained from legal journal for case laws. The study found eight potential legal risks. Among the potential legal risks are failure to provide safe escape route and leak of patient medical information during patient transfer. Failure to provide safe escape route falls under Occupier’s Liability (Law of Tort). Leak of patient medical information during patient transfer falls under Breach of Medical Confidentiality (Law of Tort). The study finds that it is not sufficient for a hospital to identify legal risks. Knowledge of relevant branch of law is critical to understand hospital legal liabilities during crisis.

“The Native Court Way”

Abstract This article examines surviving native court records from 1905–1957 in Abeokuta, Southwest Nigeria, to argue that what constituted marriage, marital rights, and sexual access to wives was changing readily in this period of socioeconomic and political change. In this period, Britain established the native court system, stressing African and British judges, to apply rigid ideas of native law and customs concerning marriage. Men and women—husbands, wives, lovers, fathers, uncles, aunties, brothers, sisters, and in-laws—approached the native courts to negotiate conflict over marriage, divorce, seduction, adultery, and child custody. Rather than administering rigid legal judgements of what constituted legitimate marriage, judgements rendered by these courts provided maneuverability, specifically for women to negotiate and contest marital status and relations.

Clamouring for Legal Protection: What the Great Books Teach Us About People Fleeing from Persecution. By Robert F. Barsky.

In this book, Robert F. Barsky provides new readings of the ‘Great Books’ (a.k.a. canonical literature) through a refugee studies perspective. Although Barsky’s book is of interest to anyone interested in literature and/or refugees, it is primarily addressed to law students, and situates itself in the ‘the law-and-literature movement’ that is ‘based on the notion that the engagement of law students and lawyers with literature about law and lawyering can help develop or maintain ethical sensibilities’ (p. vii). In fact, although the nexus between law and literature appears to be incongruent in the first glance, Barsky shows how literary references can often be found in legal judgments (p. 23). The book has five chapters based on key topics related to refugees along with the introduction and the conclusion. In these chapters, Barsky offers readings of canonical literature that highlight their hitherto suppressed ‘refugee-like situations’ (p. ix). While this is certainly a novel approach since such a sustained reading of the canon from a refugee studies perspective has not been previously attempted, some of Barsky’s readings come across as more compelling than others.

정신질환(우울증)으로 인한 자살시 보험약관상 면책조항의 적용 기준

If the insured commits suicide due to mental illness such as depression in insurance practice, there are many disputes over whether the accident was intentional or caused the result of death without being able to make free decisions due to mental and physical loss. The target judgment is also that elementary school teacher is under extreme stress from the student's parents' verbal abuse, afterwards, she was diagnosed with depression and treated at a psychiatrist, and about three years later, she hanged herself at home after work. The Supreme Court judged that the appellate court's decision did not take into account the opinions of psychiatrists and the results of administrative litigation of survivor’s compensation by misunderstanding the law on the interpretation of the reasons for immunity in the insurance contract’s policy, therefore, the Supreme Court sentenced a ruling that was completely contrary to the judgment of the appellate court.
 In fact, mental and physical loss is the lack of discrimination and decision-making ability for objects due to mental and physical disabilities, whether there was mental and physical loss is not determined by the medical degree, but it belongs to a legal and normative judgment issue that judges should decide based on expert emotions. Therefore, considering the text and purpose of the provision for restricting suicide immunity, it is reasonable to interpret it narrowly as “a state in which free decision-making cannot be made” means a state in which there is no ‘awareness’ and ‘will’ of the consequences of death, such as mental and physical loss. In this regard, I think it is unfair that the target judgment judged that the insured's death committed suicide without being able to make free decision. Because the Supreme Court too broadly recognized the scope of death due to injury, focusing only on the protection of the bereaved families.
 I think it is necessary to revise the standard policy to define the concept of 'losing mind and body' and 'state in which free decision-making cannot be made' as a specific and objective criterion by referring to the above seven judgment elements.

영국의 중복집회 관련 입법례 및 판례 분석

Britain has traditionally recognized the right to assembly and demonstration as one of the basic rights of its citizens, and there has been no written law. In 1998, while recognizing the domestic legal effect of the European Convention on Human Rights, the right to assembly was also accepted in society. However, there is a limitation that the statutory law does not regulate the overlapping assemblies which have various problems. Nevertheless, English courts present a legal judgment on the issue of overlapping assemblies based on the relevant provisions of the European Convention on Human Rights and the precedents of the European Court of Human Rights. Regardless of the order of notification of overlapping assemblies, it is judged first whether the substantive contents of the assemblies conform to the characteristics of the rights to be protected by the European Convention on Human Rights, and whether an assembly is worthy of protection as a 'peaceful assembly'. Even if intervention by state agencies is unavoidable, such interference must minimally violate the right to assembly, and must have a legal basis, a legitimate purpose, and a necessity for a democratic society. It is understood that, on the basis of these conditions, state bodies may prohibit or restrict overlapping gatherings. This tendency is interpreted as suggesting that multiple factors should be substantially evaluated for each case, rather than formally limiting the overlapping assemblies.

РАЦИОНАЛЬНОЕ ИСПОЛЬЗОВАНИE ПРИРОДНЫХ РЕСУРСОВ В РЕСПУБЛИКЕ УЗБЕКИСТАН: ВОПРОСЫ ПРАВОВОГО ОБЕСПЕЧЕНИЯ

This article analyzes the role and importance of legal support for the rational use of natural resources. Based on scientific and legal judgments, the main directions of the environmental policy of the state in the field of rational use of natural resources and issues of further improvement of natural resource legislation are substantiated. The author pays special attention to the definition of such concepts as: “use of nature”, “use of natural resources”, “rational use of natural resources”, “sustainable development” and “legal regime for the rational use of natural resources”. The general and specific features of the legislative acts of the Republic of Uzbekistan, in the field of rational use of land, water, subsoil, flora and fauna are analyzed. The main shortcomings of the legislation in this area are outlined; conclusions and recommendations are outlined for improving legislation in the field of rational use of natural resource legislation.