This paper presents TENJI, a system for exploring a knowledge graph based on legal textbooks, norms, and court decisions. TENJI reveals relationships between legal documents by enabling traversal of citation graphs and references extracted from textbooks. Since textbooks provide contextual legal knowledge that is not always explicit in the norms, TENJI uncovers hidden connections. We followed Human-Centered Design principles to ensure a user-friendly experience.

The concept of human-centeredness exists in the fields of software ergonomics and artificial intelligence. In this work, we propose how key principles from both disciplines can be applied together in a unified software design process. While the research community for legal artificial intelligence is well-aware of common requirements, such as explainability and privacy, work on Human-Centered Design focusing on creating and evaluating the user experience is rare. We contribute a blueprint for future legal system design optimized for user experience and common requirements of legal artificial intelligence applications.

In this work, we propose a hybrid approach for legal norm retrieval that combines the structural information modeled in knowledge graphs with the textual content of legal documents. Our method utilizes the intricate relationships within the Japanese Civil Code, supplemented by relevant precedents, references, commentary, and mentions in legal textbooks on Japanese law. We assess the effectiveness of our approach in Task 3 of the Competition on Legal Information Extraction/Entailment (COLIEE), using both a transformer model and BM25 as a more explainable retrieval model. In our experiments, we examine the contributions of the different legal document types, showing the positive impact of the knowledge graph and auxiliary information.

In this paper, we present LUMI, a system that explains document retrieval through span highlighting. LUMI allows users to select a query span and highlights the most relevant part of a retrieved document using transformer-based retrieval, improving transparency in legal and technical analysis.

As governments worldwide continue to release vast amounts of textual information, the need for efficient and insightful tools to extract, interpret and present this data has become increasingly critical. Towards solving this issue, we present the BUNDESTAG-MINE: an environment that periodically retrieves pertinent data from the German parliament, parses and analyzes it using pipelines for natural language processing, and then displays the results in a web application that is publicly accessible. BUNDESTAG-MINE helps to extract key information from parliamentary documents in a visually appealing matter for many use cases. For instance, the tool can be leveraged by journalists for news detection, lawyers for compliance checking, linguists for discourse analysis, and the broad public to inform themselves about the positions of political party members on a topic.

To satiate the comprehensive information need of users, retrieval systems surpassing the boundaries of language are inevitable in the present digital space in the wake of an ever-rising multilingualism. This work presents the first-of-its-kind Bilingual Text Retrieval Explanations (BiTe-REx) aimed at users performing competitor or wage analysis in the automotive domain. BiTe-REx supports users to gather a more comprehensive picture of their query by retrieving results regardless of the query language and enables them to make a more informed decision by exposing how the underlying model judges the relevance of documents. With a user study, we demonstrate statistically significant results on the understandability and helpfulness of the explanations provided by the system.

In this work, we examine variations of the BERT model on the statute law retrieval task of the COLIEE competition. This includes approaches to leverage BERT's contextual word embeddings, fine-tuning the model, combining it with TF-IDF vectorization, adding external knowledge to the statutes and data augmentation. Our ensemble of Sentence-BERT with two different TF-IDF representations and document enrichment exhibits the best performance on this task regarding the F2 score. This is followed by a fine-tuned LEGAL-BERT with TF-IDF and data augmentation and our third approach with the BERTScore. As a result, we show that there are significant differences between the chosen BERT approaches and discuss several design decisions in the context of statute law retrieval.

This research presents a recommender system designed on the basis of a bottom-up knowledge base from textbooks. While other ontologies that are usually applied to such tasks are hand-crafted, our automated approach is a possible answer to the knowledge acquisition bottleneck. We extract concept hierarchies from section titles and use co-occurrences in book sections as evidence for possible contextual relationships between the therein mentioned entities. Motivated by a legal use case of recommending upcoming changes in law, the design is targeting three major challenges: different abstraction levels between entities of legal documents and the parliament protocols announcing norm changes, as well as engineering an explainable retrieval mechanism using the knowledge base which can additionally offer decent usability despite a high-recall requirement. Although the system is developed for a specific legal use case, there are many aspects of general applicability in the fields of recommender systems, information retrieval and information extraction, entity resolution, explainable artificial intelligence and usability. We validate selected parts of the system design also on other applications, such as educational media research.

As legal regulations evolve, companies and organizations are tasked with quickly understanding and adapting to regulation changes. Tools like legal knowledge bases can facilitate this process, by either helping users navigate legal information or become aware of potentially relevant updates. At their core, these tools require legal references from many sources to be unified, e.g., by legal entity linking. This is challenging since legal references are often implicitly expressed, or combined via a context. In this paper, we prototype a machine learning approach to link legal references and retrieve combinations for a given context, based on standard features and classifiers, as used in entity resolution. As an extension, we evaluate an enhancement of those features with topic vectors, aiming to capture the relevant context of the passage containing a reference.We experiment with a repository of authoritative sources on German law for building topic models and extracting legal references and report that topic models do indeed contribute in improving supervised entity linking and reference retrieval.