Case law retrieval is the task of locating truly relevant legal cases given an input query case. Unlike information retrieval for general texts, this task is more complex with two phases (legal case retrieval and legal case entailment) and much harder due to a number of reasons. First, both the query and candidate cases are long documents consisting of several paragraphs. This makes it difficult to model with representation learning that usually has (...) restriction on input length. Second, the concept of relevancy in this domain is defined based on the legal relation that goes beyond the lexical or topical relevance. This is a real challenge because normal text matching will not work. Third, building a large and accurate legal case dataset requires a lot of effort and expertise. This is obviously an obstacle to creating enough data for training deep retrieval models. In this paper, we propose a novel approach called supporting model that can deal with both phases. The underlying idea is the case–case supporting relation and the paragraph–paragraph as well as the decision-paragraph matching strategy. In addition, we propose a method to automatically create a large weak-labeling dataset to overcome the lack of data. The experiments showed that our solution has achieved the state-of-the-art results for both case retrieval and case entailment phases. (shrink)

Legal text retrieval traditionally relies upon external knowledge sources such as thesauri and classification schemes, and an accurate indexing of the documents is often manually done. As a result not all legal documents can be effectively retrieved. However a number of current artificial intelligence techniques are promising for legal text retrieval. They sustain the acquisition of knowledge and the knowledge-rich processing of the content of document texts and information need, and of their matching. Currently, techniques for learning information (...) needs, learning concept attributes of texts, information extraction, text classification and clustering, and text summarization need to be studied in legal text retrieval because of their potential for improving retrieval and decreasing the cost of manual indexing. The resulting query and text representations are semantically much richer than a set of key terms. Their use allows for more refined retrieval models in which some reasoning can be applied. This paper gives an overview of the state of the art of these innovativetechniques and their potential for legal text retrieval. (shrink)

The paper documents the post-war retrenchment and failure of the post-war British Consumer Co-operative Movement. In contrast to the general failure one CEO, Terry Thomas stands out both for his success in co-operative rebranding and returning to profitability the UK Co-operative Bank and because he alone amongst the top echelons of the Co-operative Groups Management based his strategies on a clearly articulated philosophy based on his understanding of the values and purpose of the co-operative movement rooted in its historical traditions (...) grounded in the writings and achievements of Robert Owen, The paper goes on to provide a case study of the bank’s process of transformation from loss-making subsidiary to the first positive co-operative national brand in the post-war period of its history. The author argues that lack of appropriate vision based on the founding values and purposes of the Co-operative Movement is the principal reason for the management’s and governance failures that have beset the UK Co-operative Group. Instead of using the past to help in understanding the present and planning for the future, the UK Co-operative Group Leadership ignored it or worse used the past successes to congratulate itself and disguise its manifest failures. In this, they were supported by an uncritical Co-operative Union. Davis argues large co-operatives cannot be managed by a civil service responsible to an elected board. Co-operatives need a servant-leadership model of professional management dedicated to the transformational goals set by the founders of the co-operative movement. This needs a radical rethink and promotion of co-operative management education and a dedicated executive recruitment that seeks out value-based professionals whose attitudes and values are compatible with Co-operative values, ownership and purpose. (shrink)

In this paper we take a fresh look at the information retrieval problem of balancing recall with precision in electronic document extraction. We examine the IR constructs of uncertainty, context and relevance, proposing a new process model for context learning, and introducing a new IT artifact designed to support user driven learning by leveraging explicit knowledge to discover implicit knowledge within a corpus of documents. The IT artifact is a prototype designed to present a small set of extracted (...) documents from a targeted corpus based upon user inputted criteria. The prototype provides the user with the opportunity to balance exploration and exploitation, via iterative relevance feedback to address the problem of imprecision resulting from uncertainty. We model the problem as an exploration–exploitation dilemma and apply it to a specific case of IR called eDiscovery. We conduct a series of behavioral experiments to evaluate the model and the artifact. Our initial findings indicate that the proposed model and the artifact improve performance in the IR result. (shrink)

Automatic summarization of legal case judgements, which are known to be long and complex, has traditionally been tried via extractive summarization models. In recent years, generative models including abstractive summarization models and Large language models (LLMs) have gained huge popularity. In this paper, we explore the applicability of such models for legal case judgement summarization. We applied various domain-specific abstractive summarization models and general-domain LLMs as well as extractive summarization models over two sets of legal case judgements (...) – from the United Kingdom (UK) Supreme Court and the Indian Supreme Court – and evaluated the quality of the generated summaries. We also perform experiments on a third dataset of legal documents of a different type – Government reports from the United States. Results show that abstractive summarization models and LLMs generally perform better than the extractive methods as per traditional metrics for evaluating summary quality. However, detailed investigation shows the presence of inconsistencies and hallucinations in the outputs of the generative models, and we explore ways to reduce the hallucinations and inconsistencies in the summaries. Overall, the investigation suggests that further improvements are needed to enhance the reliability of abstractive models and LLMs for legal case judgement summarization. At present, a human-in-the-loop technique is more suitable for performing manual checks to identify inconsistencies in the generated summaries. (shrink)

The escalating number of pending cases is a growing concern worldwide. Recent advancements in digitization have opened up possibilities for leveraging artificial intelligence (AI) tools in the processing of legal documents. Adopting a structured representation for legal documents, as opposed to a mere bag-of-words flat text representation, can significantly enhance processing capabilities. With the aim of achieving this objective, we put forward a set of diverse attributes for criminal case proceedings. To enhance the effectiveness of automatically extracting these attributes (...) from legal documents within a sequence labeling framework, we propose the utilization of a few-shot learning approach based on Large Language Models (LLMs). Moreover, we demonstrate the efficacy of the extracted attributes in downstream tasks, such aslegal judgment prediction and legal statute prediction. (shrink)

In a Common Law system, legal practitioners need frequent access to prior case documents that discuss relevant legal issues. Case documents are generally very lengthy, containing complex sentence structures, and reading them fully is a strenuous task even for legal practitioners. Having a concise overview of these documents can relieve legal practitioners from the task of reading the complete case statements. Legal catchphrases are (multi-word) phrases that provide a concise overview of the contents of a case (...) document, and automated generation of catchphrases is a challenging problem in legal analytics. In this paper, we propose a novel supervised neural sequence tagging model for the extraction of catchphrases from legal case documents. Specifically, we show that incorporating document-specific information along with a sequence tagging model can enhance the performance of catchphrase extraction. We perform experiments over a set of Indian Supreme Court case documents, for which the gold-standard catchphrases (annotated by legal practitioners) are obtained from a popular legal information system. The performance of our proposed method is compared with that of several existing supervised and unsupervised methods, and our proposed method is empirically shown to be superior to all baselines. (shrink)

The BankXX system models the process of perusing and gathering information for argument as a heuristic best-first search for relevant cases, theories, and other domain-specific information. As BankXX searches its heterogeneous and highly interconnected network of domain knowledge, information is incrementally analyzed and amalgamated into a dozen desirable ingredients for argument (called argument pieces), such as citations to cases, applications of legal theories, and references to prototypical factual scenarios. At the conclusion of the search, BankXX outputs the set of argument (...) pieces filled with harvested material relevant to the input problem situation.This research explores the appropriateness of the search paradigm as a framework for harvesting and mining information needed to make legal arguments. In this article, we describe how legal research fits the heuristic search framework and detail how this model is used in BankXX. We describe the BankXX program with emphasis on its representation of legal knowledge and legal argument. We describe the heuristic search mechanism and evaluation functions that drive the program. We give an extended example of the processing of BankXX on the facts of an actual legal case in BankXX's application domain — the good faith question of Chapter 13 personal bankruptcy law. We discuss closely related research on legal knowledge representation and retrieval and the use of search for case retrieval or tasks related to argument creation. Finally we review what we believe are the contributions of this research to the understanding of the diverse disciplines it addresses. (shrink)

Large Language Models (LLMs) could be a useful tool for lawyers. However, empirical research on their effectiveness in conducting legal tasks is scant. We study securities cases involving cryptocurrencies as one of numerous contexts where AI could support the legal process, studying GPT-3.5’s legal reasoning and ChatGPT’s legal drafting capabilities. We examine whether a) GPT-3.5 can accurately determine which laws are potentially being violated from a fact pattern, and b) whether there is a difference in juror decision-making based on complaints (...) written by a lawyer compared to ChatGPT. We feed fact patterns from real-life cases to GPT-3.5 and evaluate its ability to determine correct potential violations from the scenario and exclude spurious violations. Second, we had mock jurors assess complaints written by ChatGPT and lawyers. GPT-3.5’s legal reasoning skills proved weak, though we expect improvement in future models, particularly given the violations it suggested tended to be correct (it merely missed additional, correct violations). ChatGPT performed better at legal drafting, and jurors’ decisions were not statistically significantly associated with the author of the document upon which they based their decisions. Because GPT-3.5 cannot satisfactorily conduct legal reasoning tasks, it would be unlikely to be able to help lawyers in a meaningful way at this stage. However, ChatGPT’s drafting skills (though, perhaps, still inferior to lawyers) could assist lawyers in providing legal services. Our research is the first to systematically study an LLM’s legal drafting and reasoning capabilities in litigation, as well as in securities law and cryptocurrency-related misconduct. (shrink)

Given the replication crisis in cognitive science, it is important to consider what researchers need to do in order to report results that are reliable. We consider three changes in current practice that have the potential to deliver more realistic and robust claims. First, the planned experiment should be divided into two stages, an exploratory stage and a confirmatory stage. This clear separation allows the researcher to check whether any results found in the exploratory stage are robust. The second change (...) is to carry out adequately powered studies. We show that this is imperative if we want to obtain realistic estimates of effects in psycholinguistics. The third change is to use Bayesian data-analytic methods rather than frequentist ones; the Bayesian framework allows us to focus on the best estimates we can obtain of the effect, rather than rejecting a strawman null. As a case study, we investigate number interference effects in German. Number feature interference is predicted by cue-based retrieval models of sentence processing, but it has shown inconsistent results. We show that by implementing the three changes mentioned, suggestive evidence emerges that is consistent with the predicted number interference effects. (shrink)

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. (shrink)

In this work we study, design, and evaluate computational methods to support interpretation of statutory terms. We propose a novel task of discovering sentences for argumentation about the meaning of statutory terms. The task models the analysis of past treatment of statutory terms, an exercise lawyers routinely perform using a combination of manual and computational approaches. We treat the discovery of sentences as a special case of ad hoc document retrieval. The specifics include retrieval of short texts, (...) specialized document types, and, above all, the unique definition of document relevance provided in detailed annotation guidelines. To support our experiments we assembled a data set comprising 42 queries which we plan to release to the public in the near future in order to support further research. Most importantly, we investigate the feasibility of developing a system that responds to a query with a list of sentences that mention the term in a way that is useful for understanding and elaborating its meaning. This is accomplished by a systematic assessment of different features that model the sentences’ usefulness for interpretation. We combine features into a compound measure that accounts for multiple aspects. The definition of the task, the assembly of the data set, and the detailed task analysis provide a solid foundation for employing a learning-to-rank approach. (shrink)

Similar case analysis (SCA) is an essential topic in legal artificial intelligence, serving as a reference for legal professionals. Most existing works treat SCA as a traditional text classification task and ignore some important legal elements that affect the verdict and case similarity, like legal events, and thus are easily misled by semantic structure. To address this issue, we propose a Legal Event-Context Model named LECM to improve the accuracy and interpretability of SCA based on Chinese legal (...) corpus. The event-context integration mechanism, which is an essential component of the LECM, is proposed to integrate the legal event and context information based on the attention mechanism, enabling legal events to be associated with their corresponding relevant contexts. We introduce an event detection module to obtain the legal event information, which is pre-trained on a legal event detection dataset to avoid labeling events manually. We conduct extensive experiments on two SCA tasks, i.e., similar case matching (SCM) and similar case retrieval (SCR). Compared with baseline models, LECM is validated by about 13% and 11% average improvement in terms of mean average precision and accuracy respectively, for SCR and SCM tasks. These results indicate that LECM effectively utilizes event-context knowledge to enhance SCA performance and its potential application in various legal document analysis tasks. (shrink)

Recently, the pandemic caused by COVID-19 is severe in the entire world. The prevention and control of crimes associated with COVID-19 are critical for controlling the pandemic. Therefore, to provide efficient and convenient intelligent legal knowledge services during the pandemic, we develop an intelligent system for legal information retrieval on the WeChat platform in this paper. The data source we used for training our system is “The typical cases of national procuratorial authorities handling crimes against the prevention and control (...) of the new coronary pneumonia pandemic following the law”, which is published online by the Supreme People’s Procuratorate of the People’s Republic of China. We base our system on convolutional neural network and use the semantic matching mechanism to capture inter-sentence relationship information and make a prediction. Moreover, we introduce an auxiliary learning process to help the network better distinguish the relation between two sentences. Finally, the system uses the trained model to identify the information entered by a user and responds to the user with a reference case similar to the query case and gives the reference legal gist applicable to the query case. (shrink)

Mental model theory has been used to explain many differing phenomena in adult reasoning, including the extensively studied case of conditional reasoning. However, the current theory makes predictions about the development of conditional reasoning that are not consistent with data. In this article, young children's performance on conditional reasoning problems and the justifications given are analysed. A mental model account of conditional reasoning is proposed that assumes that (1) young children can reason with two models and (2) (...) the fleshing out of conditionals involves activation of information in semantic memory that uses the minor premise as a retrieval cue. (shrink)

Reasoners compare problems to prior cases to draw conclusions about a problem and guide decision making. All Case-Based Reasoning (CBR) employs some methods for generalizing from cases to support indexing and relevance assessment and evidences two basic inference methods: constraining search by tracing a solution from a past case or evaluating a case by comparing it to past cases. Across domains and tasks, however, humans reason with cases in subtly different ways evidencing different mixes of and mechanisms (...) for these components.In recent CBR research in Artificial Intelligence (AI), five paradigmatic approaches have emerged: statistically-oriented, model-based, planning/design-oriented, exemplar-based, and adversarial or precedent-based. The paradigms differ in the assumptions they make about domain models, the extent to which they support symbolic case comparison, and the kinds of inferences for which they employ cases. (shrink)

The general mitigating and aggravating circumstances of criminal liability are elements attached to the crime that, when they occur, affect the punishment quantum. Cuban criminal legislation provides a catalog of such circumstances and some general conditions for their application. Such norms give judges broad discretion in assessing circumstances and adjusting punishment based on the intensity of those circumstances. In the interest of broad judicial discretion, the law does not establish specific ways for measuring circumstances’ intensity. This gives judges more freedom (...) and autonomy, but it also imposes on them more social responsibility and challenges them to manage the uncertainty and subjectivity inherent in this complex activity. This paper proposes a model to aid the linguistic assessment of circumstances’ intensity and to provide linguistic and numerical recommendations to determine an appropriate punishment interval. M-LAMAC determines the collective evaluation of circumstances of the same type, determines the prevalence of a type of circumstance by means of a compensation function, recommends the required modification in the input interval, and finally recommends a numerical interval adjusted to the judges’ initially expressed preferences. The model’s applicability is demonstrated by means of several experiments on a fictitious case of bank document forgery. (shrink)

In the domain of legal information retrieval, an important challenge is to compute similarity between two legal documents. Precedents 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 and Doc2Vec 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 and Law2Vec. It is observed that the more traditional methods that rely on a bag-of-words representation performs better than the more advanced context-aware methods 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. (shrink)

We propose simple nonlinear mathematical models for the legal concept of balancing of interests. Our aim is to bridge the gap between an abstract formalisation of a balancing decision while assuring consistency and ultimately legal certainty across cases. We focus on the conflict between the rights to privacy and to the protection of personal data in Art. 7 and Art. 8 of the EU Charter of Fundamental Rights (EUCh) against the right of access to information derived from Art. 11 EUCh. (...) These competing rights are denoted by ( \(i_1\) ) _right to privacy _ and ( \(i_2\) ) _access to information_; mathematically, their indices are respectively assigned by \(u_1\in [0,1]\) and \(u_2\in [0,1]\) subject to the constraint \(u_1+u_2=1\). This constraint allows us to use one single index _u_ to resolve the conflict through balancing. The outcome will be concluded by comparing the index _u_ with a prior given threshold \(u_0\). For simplicity, we assume that the balancing depends on only selected legal criteria such as the social status of affected person, and the sphere from which the information originated, which are represented as inputs of the models, called legal parameters. Additionally, we take “time” into consideration as a legal criterion, building on the European Court of Justice’s ruling on the right to be forgotten: by considering time as a legal parameter, we model how the outcome of the balancing changes over the passage of time. To catch the dependence of the outcome _u_ by these criteria as legal parameters, data were created by a fully-qualified lawyer. By comparison to other approaches based on machine learning, especially neural networks, this approach requires significantly less data. This might come at the price of higher abstraction and simplification, but also provides for higher transparency and explainability. Two mathematical models for _u_, a time-independent model and a time-dependent model, are proposed, that are fitted by using the data. (shrink)

This paper introduces an advanced event detection model for legal intelligence, focusing on identifying event types in legal cases by examining trigger word candidates. It employs the DeBERTa pre-trained language model for encoding sentences into enriched word representations, supplemented by the Global Pointer neural network for initial scoring. The model further uses a graph convolutional network, conditional layer normalisation, and a convolutional neural network to extract features from these representations. A multilayer perceptron then determines the event type (...) based on these features and initial scores. Additionally, a dictionary-matching method revises the predicted event types, with adversarial training and a sentence-length mask employed to enhance model performance and address missing trigger words. The model’s effectiveness is proven through extensive experimentation, outperforming state-of-the-art baselines (including some large language models) and securing third prize in the event detection task at the Challenge of AI in Law (CAIL) 2022. The code of our model is available at https://github.com/1gst/DGGCCN/tree/main. (shrink)

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. (shrink)

Hypertext may represent a new paradigm capable of exploring legal sources within which links are established according to pertinent relationships found between statute texts and case law. However, to discover relevant information in such a network, a browsing mechanism is not enough when faced with a large volume of texts. This paper describes a new retrieval model where documents are represented according to both their content and relationships with other sources of information.

This article discusses the desirability and feasibility of modeling precedents with multiple interpretations within factor-based models of precedential constraint. The main idea is that allowing multiple reasonable interpretations of cases and modeling precedential constraint as a function of what all reasonable interpretations compel may be advantageous. The article explains the potential benefits of extending the models in this way with a focus on incorporating a theory of vertical precedent in U.S. federal appellate courts. It also considers the costs of extending (...) the models in this way, such as the significant increase in the functional size of the case base and the need to provide some kind of ordering on interpretations to select a “best” interpretation. Finally, the article suggests partially incorporating multiple interpretations of dimensions as a realistic starting point for incorporating interpretations generally, and shows how doing so can help address difficulties with dimensions. The conclusion remarks on the use of interpretations to deal with inconsistent precedents. (shrink)

Accurate identification of legal provisions is crucial for adjudicating criminal cases, but the complexity and volume of legal texts pose significant challenges for legal professionals. This paper addresses these challenges by introducing a novel legal provision selection framework that transforms the task from a simple classification problem into a sophisticated system combining semantic matching with causal relationship learning. Leveraging large language models, our approach enhances the understanding and interpretation of legal language, by extracting nuanced features from legal texts for deeper (...) contextual comprehension. Additionally, integrating causal learning aligns with the inherent causality in legal reasoning, improving model interpretability and mitigating data bias. Our method demonstrates superior accuracy and robustness through extensive experiments on the CAIL2018 dataset and its subsets. This research significantly advances legal AI applications, promoting efficiency and fairness in the criminal justice system by providing precise and reliable legal provision selection. (shrink)

Legal Judgment Summarization (LJS) can highly summarize legal judgment documents, improving judicial work efficiency in case retrieval and other occasions. Legal judgment documents are usually lengthy; however, most existing LJS methods are directly based on general text summarization models, which cannot handle long texts effectively. Additionally, due to the complex structural characteristics of legal judgment documents, some information may be lost by applying only one single kind of summarization model. To address these issues, we propose an integrated (...) summarization method which leverages both semantic and structural information to improve the quality of LJS. Specifically, legal judgment documents are firstly segmented into three relatively short parts according to their specific structure. We propose an extractive summarization model named BSLT and an abstractive summarization model named LPGN by adopting Lawformer as the encoder. Lawformer is a new pre-trained language model for long legal documents, which specializes in capturing long-distance dependency and modeling legal semantic features. Then, we adopt different models to summarize the corresponding part regarding its structural characteristics. Finally, the obtained summaries are integrated to generate a high-quality summary involving semantic and structural information. We conduct comparative experiments to evaluate the performance of our model. The results show that our model outperforms the baseline model LEAD-3 by 14.78% on the mean ROUGE score, which demonstrates our method is effective in LJS and is prospected to be applied to assist other tasks in legal artificial intelligence. (shrink)

Online dispute resolution (ODR) is an alternative to traditional litigation that can both significantly reduce the disadvantages suffered by litigants unable to afford an attorney and greatly improve court efficiency and economy. An important aspect of many ODR systems is a facilitator, a neutral party who guides the disputants through the steps of reaching an agreement. However, insufficient availability of facilitators impedes broad adoption of ODR systems. This paper describes a novel model of facilitation that integrates two distinct but (...) complementary knowledge sources: cognitive task analysis of facilitator behavior and corpus analysis of ODR session transcripts. This model is implemented in a decision-support system that (1) monitors cases to detect situations requiring immediate attention and (2) automates selection of standard text messages appropriate to the current state of the negotiations. This facilitation model has the potential to compensate for shortages of facilitators by improving the efficiency of experienced facilitators, assisting novice facilitators, and providing autonomous facilitation. (shrink)

With the ever-growing accessibility of case law online, it has become challenging to manually identify case law relevant to one’s legal issue. In the Netherlands, the planned increase in the online publication of case law is expected to exacerbate this challenge. In this paper, we tried to predict whether court decisions are cited by other courts or not after being published, thus in a way distinguishing between more and less authoritative cases. This type of system may be (...) used to process the large amounts of available data by filtering out large quantities of non-authoritative decisions, thus helping legal practitioners and scholars to find relevant decisions more easily, and drastically reducing the time spent on preparation and analysis. For the Dutch Supreme Court, the match between our prediction and the actual data was relatively strong (with a Matthews Correlation Coefficient of 0.60). Our results were less successful for the Council of State and the district courts (MCC scores of 0.26 and 0.17, relatively). We also attempted to identify the most informative characteristics of a decision. We found that a completely explainable model, consisting only of handcrafted metadata features, performs almost as well as a less well-explainable system based on all text of the decision. (shrink)

Pronoun interpretation is often described as relying on a comprehender's mental model of discourse. For example, in some psycholinguistic accounts, interpreting pronouns involves a process of retrieval, whereby a pronoun is resolved by accessing information from its linguistic antecedent. However, linguistic antecedents are neither necessary nor sufficient for interpreting a pronoun, and even when an antecedent has been introduced in earlier discourse, there is little evidence for the retrieval of linguistic form. The current study extends our understanding (...) of pronoun interpretation by examining whether the semantics of antecedent expressions are retrieved from representations of past discourse. Participants were instructed to move displayed objects in a Visual World eye-tracking task. In some cases, the semantics of the antecedent were no longer viable after an instruction was completed (e.g., “Move the house on the left to area 12,” where the result was that a different house is now the leftmost one). In this case, retrieving antecedent semantics at the point of hearing a subsequent pronoun (“Now, move it…”) should entail a processing penalty. Instead, the results showed that antecedent semantics have no direct effect on interpretation, raising additional questions about the role that retrieval might play in pronoun interpretation. (shrink)

Technology has substantially transformed the way legal services operate in many different countries. With a large and complex collection of digitized legal documents, the judiciary system worldwide presents a promising scenario for the development of intelligent tools. In this work, we tackle the challenging task of organizing and summarizing the constantly growing collection of legal documents, uncovering hidden topics, or themes that later can support tasks such as legal case retrieval and legal judgment prediction. Our approach to this (...) problem relies on topic discovery techniques combined with a variety of preprocessing techniques and learning-based vector representations of words, such as Doc2Vec and BERT-like models. The proposed method was validated using four different datasets composed of short and long legal documents in Brazilian Portuguese, from legal decisions to chapters in legal books. Analysis conducted by a team of legal specialists revealed the effectiveness of the proposed approach to uncover unique and relevant topics from large collections of legal documents, serving many purposes, such as giving support to legal case retrieval tools and also providing the team of legal specialists with a tool that can accelerate their work of labeling/tagging legal documents. (shrink)

This paper is an introduction to a virtual special issue of AI and Law exploring the legacy of the influential HYPO system of Rissland and Ashley. The papers included are: Arguments and cases: An inevitable intertwining, BankXX: Supporting legal arguments through heuristic retrieval, Modelling reasoning with precedents in a formal dialogue Game, A note on dimensions and factors, An empirical investigation of reasoning with legal cases through theory construction and application, Automatically classifying case texts and predicting outcomes, A (...) factor-based definition of precedential constraint and An improved factor based approach to precedential constraint. After describing HYPO, in this introduction to the special issue I look at various aspects of its influence on AI and Law: the developments led by Rissland at Amherst; the developments led by Ashley in Pittsburgh; the expression of these ideas in terms of rule based systems, and their subsequent formalisation; value based theories, which were inspired by a critique of HYPO; and contemporary approaches which revive the idea of dimensions. (shrink)

The Toulmin model has been proved useful in law and argumentation theory. This model describes the basic process in justifying a claim, which comprises six elements, i.e., claim (C), data (D), warrant (W), backing (B), qualifier (Q), and rebuttal (R). Specifically, in justifying a claim, one must put forward ‘data’ and a ‘warrant’, whereas the latter is authorized by ‘backing’. The force of the ‘claim’ being justified is represented by the ‘qualifier’, and the condition under which the claim (...) cannot be justified is represented as the ‘rebuttal’. To further improve the model, (Goodnight, Informal Logic 15:41–52, 1993) points out that the selection of a backing needs justification, which he calls legitimation justification. However, how such justification is constituted has not yet been clarified. To identify legitimation justification, we separate it into two parts. One justifies a backing’s eligibility (legitimation justification 1 ; LJ 1 ); the other justifies its superiority over other eligible backings (legitimation justification 2 ; LJ 2 ). In this paper, we focus on LJ 1 and apply it to the legal justification (of judgements) in hard cases for illustration purposes. We submit that LJ 1 refers to the justification of the legal interpretation of a norm by its backing, which can be further separated into several orderable subjustifications. Taking the subjustification of a norm’s existence as an example, we show how it would be influenced by different positions in the philosophy of law. Taking the position of the theory of natural law, such subjustification is presented and evaluated. This paper aims not only to inform ongoing theoretical efforts to apply the Toulmin model in the legal field, but it also seeks to clarify the process in the justification of legal judgments in hard cases. It also offers background information for the possible construction of related AI systems. In our future work, LJ 2 and other subjustifications of LJ 1 will be discussed. (shrink)

Judgments concerning animals have arisen across a variety of established practice areas. There is, however, no publicly available repository of judgments concerning the emerging practice area of animal protection law. This has hindered the identification of individual animal protection law judgments and comprehension of the scale of animal protection law made by courts. Thus, we detail the creation of an initial animal protection law repository using natural language processing and machine learning techniques. This involved domain expert classification of 500 judgments (...) according to whether or not they were concerned with animal protection law. 400 of these judgments were used to train various models, each of which was used to predict the classification of the remaining 100 judgments. The predictions of each model were superior to a baseline measure intended to mimic current searching practice, with the best performing model being a support vector machine (SVM) approach that classified judgments according to term frequency—inverse document frequency (TF-IDF) values. Investigation of this model consisted of considering its most influential features and conducting an error analysis of all incorrectly predicted judgments. This showed the features indicative of animal protection law judgments to include terms such as ‘welfare’, ‘hunt’ and ‘cull’, and that incorrectly predicted judgments were often deemed marginal decisions by the domain expert. The TF-IDF SVM was then used to classify non-labelled judgments, resulting in an initial animal protection law repository. Inspection of this repository suggested that there were 175 animal protection judgments between January 2000 and December 2020 from the Privy Council, House of Lords, Supreme Court and upper England and Wales courts. (shrink)

In this paper, we investigate the model of decentralized groupwise e-commerce through regional chains combined with edge computing algorithms and design and implement it. A blockchain-based architecture for remote sensing resource and service transactions is proposed. The architecture utilizes the characteristics of nontamperable and traceable data on the blockchain to solve the problem of mutual distrust between the transaction parties, uses MongoDB for data retrieval and filtering to solve the problem that it is difficult to query flexibly on (...) the blockchain, uses the file platform to save public resources to solve the problem that it is very expensive or even infeasible to store images or large texts in the blockchain, and ensures remote sensing resources and services related to the effective storage of images and description texts. The Ethernet features are described and analyzed to assess their suitability as a technical basis for the corresponding solutions. To assess the ability of the Ethernet-based system to solve solvable problems, its practical use cases are analyzed. The results of the analysis show that five main issues need to be addressed when applying Ethernet to e-commerce, namely, low scalability, lack of distributed storage, lack of convenience, reliability, and functional integrity. To exploit the idea of using blockchain technology to solve complex problems and to overcome the challenges identified in the existing Ethernet-based implementation solutions, an optimization idea is proposed by creating a multiblockchain architecture based multimodule solution in the Ethernet framework. Finally, the application prospects of the proposed information system are discussed. (shrink)

Online forums have become the main source of knowledge over the Internet as data are constantly flooded into them. In most cases, a question in a web forum receives several responses, making it impossible for the question poster to obtain the most suitable answer. Thus, an important problem is how to automatically extract the most appropriate and high-quality answers in a thread. Prior studies have used different combinations of both lexical and nonlexical features to retrieve the most relevant answers from (...) discussion forums, and hence, there is no standard/general set of features that could be effectively used for relevant answer/reply post classification. However, this study proposed an answer detection model that is exclusively relying on lexical features and employs a random forest classifier for classification of answers in discussion boards. Experimental results showed that the proposed answer detection model outperformed the baseline technique and other state-of-the-art machine learning algorithms in terms of classification accuracy on benchmark forum datasets. (shrink)

The demand for integrating and sharing heterogeneous data online has attracted the interest of cultural institutions in making information access and retrieval more effective via Semantic Web technologies. The present study proposes a digital repository for 3D scans of modernist sculptures in public spaces in the city of Rio de Janeiro, Brazil, with a view to ensuring access, use, reuse and preservation of this information. This is a qualitative exploratory experimental study based on the scientific literature and specific empirical (...) material. It presents the analysis results of vocabularies for physical artifact documents and their digital counterparts on the Semantic Web and a discussion on how these align with the nature of the metadata determined here, as well as a metadata modeling prototype implemented on the Tainacan platform and aimed at cataloging digital 3D replicas. We claim that the proposed model for documenting cultural heritage assets on Tainacan is easy to implement, in that it uses accessible technology with a wide internet user base, highly expressive in its descriptions of 3D and multimedia content and based on well-established metadata and ontology standards recommended by regulatory bodies and communities such as the World Wide Web Consortium and International Organization for Standardization. Keywords: networked heritage documents, digital repositories, 3D digitization, semantic annotation. (shrink)

Though not as widely studied as the Research Article, the abstract has attracted increasing interest among researchers over last decades. A number of contrastive or comparative studies of abstracts in English and other languages have already been carried out considering mainly the hard sciences and some soft sciences such as linguistics and history, however no cross-cultural analyses have been conducted so far between RA abstracts in English and RA abstracts in French published in the legal field. This paper seeks to (...) investigate genre variation and changes in frame sequences comparatively in English and French RA abstracts from criminology journals. Using a genre analytical approach to qualitative and quantitative data, the paper reports on two comparable corpora, i.e. English and French, of electronically retrieved abstracts from Criminology Journals published in 2014. The two corpora are composed of three journals per language, namely Criminology, Journal of Criminal Justice, Journal of Criminal Law and Criminology for the English corpus, and Champ Pénal, Criminologie, Revue Canadienne de Droit Pénal et Criminologie for the French corpus. The analysis will be carried out following two main steps, i.e. a macro-analysis and a micro-analysis. In the former step, the corpora are compared by the analysis and discussion of the basic IMRD rhetorical move structure for the RA often proposed in the literature and the additional five moves model postulated by Dos Santos with the aim of investigating the linguistic and rhetorical variation in the abstract genre from a cross-cultural perspective. In the latter, we look at frame sequences combining forms of self-mentions and frame markers, i.e. personal patterns, impersonal patterns and locational patterns. Provisional results show that the abstracts under investigation largely follow the international conventions based on the norms established by the English-speaking international academic community. However, variation across the two cultures emerged from the linguistic realizations of framework sequences. Cross-cultural implications are discussed at the close. (shrink)

We present our method for tackling a legal case retrieval task by introducing our method of encoding documents by summarizing them into continuous vector space via our phrase scoring framework utilizing deep neural networks. On the other hand, we explore the benefits from combining lexical features and latent features generated with neural networks. Our experiments show that lexical features and latent features generated with neural networks complement each other to improve the retrieval system performance. Furthermore, our experimental (...) results suggest the importance of case summarization in different aspects: using provided summaries and performing encoded summarization. Our approach achieved F1 of 65.6% and 57.6% on the experimental datasets of legal case retrieval tasks. (shrink)

In this article we argue that idealizations and limiting cases in models play an exploratory role in science. Four senses of exploration are presented: exploration of the structure and representational capacities of theory; proof-of-principle demonstrations; potential explanations; and exploring the suitability of target systems. We illustrate our claims through three case studies, including the Aharonov-Bohm effect, the emergence of anyons and fractional quantum statistics, and the Hubbard model of the Mott phase transitions. We end by reflecting on how (...) our case studies and claims compare to accounts of idealization in the philosophy of science literature such as Michael Weisberg’s three-fold taxonomy. (shrink)

The fact that most of us are ignorant on politically relevant matters presents a problem for democracy. In light of this, some have suggested that we should impose epistemic constraints on democratic participation, and specifically that the franchise be restricted along competency lines – a suggestion that in turn runs the risk of violating a long-standing condition on political legitimacy to the effect that legitimate political arrangements cannot be open to reasonable objections. The present paper therefore outlines a way to (...) solve the problem of public ignorance without restricting the franchise. The proposal involves filtering the electoral input of a universal franchise through a statistical model that simulates what the public's political preferences would have been, had they been informed on politically relevant matters. The result is modelled democracy. A case is made that such democracy both solves the problem of public ignorance and satisfies the aforementioned condition on legitimacy. (shrink)

Scribal copying is investigated as a test case for the memetic and epidemiological models for explaining the distribution of cultural items. We may hypothesize that the incidence of errors could be low enough to allow two conditions for neo-Darwinian explanation to be fulfilled: first, that there be a rather reliable mechanism for heredity, and second that occasional mutations might produce a version more likely to survive and be propagated than the exemplar. Scriptorial conventions are reviewed. Textual criticism is investigated. (...) Finally, some attention is given to the psychology of language perception and production. In conclusion, it is argued that the memetic model for cultural transmission is not generally fecund while the epidemiological model is. (shrink)

This paper develops a novel psycholinguistic parser and tests it against experimental and corpus reading data. The parser builds on the recent research into memory structures, which argues that memory retrieval is content‐addressable and cue‐based. It is shown that the theory of cue‐based memory systems can be combined with transition‐based parsing to produce a parser that, when combined with the cognitive architecture ACT‐R, can model reading and predict online behavioral measures (reading times and regressions). The parser's modeling capacities (...) are tested against self‐paced reading experimental data (Grodner & Gibson, 2005), eye‐tracking experimental data (Staub, 2011), and a self‐paced reading corpus (Futrell et al., 2018). (shrink)

Ralph Rader's model of literary activity is built up from a theory of intention. A literary work, he believes, embodies a "cognitive act,"1 an act variously characterized as a "positive constructive intention" , "an overall creative intention" . To read a literary work is to perform an answering "act of cognition" , which is in effect the comprehension of this comprehensive intention, the assigning to the work of a "single coherent meaning" . Both acts—the embodying and the assigning —are (...) one-time, single-shot performances. They are "ends" in two senses; the overall intention is the end to which everything in the work must be contributory, and its comprehension is something the reader does at the end . Rader offers this model as if it were descriptive, as if it made explicit rules of behavior we unerringly follow, rules which underlie our "tacit or intuitive capacity" of intention producing and intention retrieving; but the model is, in fact, prescriptive since it quite arbitrarily limits this same capacity: authors are limited to no more than one positive constructive intention per unit, while readers or interpreters are limited to its discovery; whatever cannot be related to that discovery or interferes with it will either be declared not to exist or, if its existence cannot be denied, it will be labeled a defect, an "unintended and unavoidable negative consequence of the artist's positive constructive intention" . · 1. My argument will engage two of Rader's articles. They are "Fact, Theory, and Literary Explanation," Critical Inquiry 1, no.2 : 245-72, and "The Concept of Genre and Eighteenth-Century Studies," in New Approaches to Eighteenth-Century Literature: Selected Papers from the English Institute , pp. 79-115. In what follows they will be referred to as Fact and Concept along with the appropriate page number. Stanley E. Fish, professor of English at John Hopkins University, responds in this essay to Ralph W. Rader's "Fact, Theory, and Literary Explanation" . Professor Fish is the author of John Skelton's Poetry, Surprised by Sin: The Reader in Paradise Lost, and Self-Consuming Artifacts: The Experience of Seventeenth-Century Literature. His other contributions to Critical Inquiry include "Interpreting the Variorum" , "CRITICAL RESPONSE: Interpreting 'Interpreting the Variorum'" , "Normal Circumstances, Literal Language, Direct Speech Acts, the Ordinary, the Everyday, the Obvious, What Goes without Saying, and Other Special Cases" , "CRITICAL RESPONSE: A Reply to John Reichert; or, How to Stop Worrying and Learn to Love Interpretation" , and "One More Time". (shrink)

This study examined the hypothesis that a key process in conditional reasoning with concrete premises involves on-line retrieval of information about potential alternate antecedents. Participants were asked to solve reasoning problems with causal conditional premises (If cause P then effect Q). These premises were inserted into short contexts. The availability of potential alternatives was varied from one context to another by adding statements that explicitly invalidated one or more of these alternatives (i.e., other causes that lead to the effect (...) Q). The invalidated alternatives differed in the degree of their semantic association to the consequent term (Q). The results show that the effect of invalidating one or more potential alternatives on the two uncertain logical forms, AC and DA, was largely determined by their relative associative strength. These results strongly support a model for conditional reasoning with causal premises that supposes that a key element in responding to the uncertain logical forms is on-line retrieval of at least one potential alternative antecedent. (shrink)