Does Travel Spread Infection?—Effects of Social Stirring Simulated on SEIRS Circuit GridOhsawa, Yukio; Kondo, Sae; Maekawa, Tomohide
doi: 10.1007/s12626-024-00156-4pmid: N/A
Previous models of the spread of viral infection could not explain the potential risk of non-infectious travelers and exceptional events, such as the reduction in infected cases with an increase in travelers. In this study, we provide an explanation for improving the model by considering two factors. First, we consider the travel of susceptible (S), exposed (E), and recovered (R) individuals who may become infected and infect others in the destination region in the near future, as well as infectious (I). Second, people living in a region and those moving from other regions are treated as separate but interacting groups to consider the potential influence of movement before infection. We show the results of the simulation of infection spread in a country where individuals travel across regions and the government chooses regions to vaccinate with priority. As a result, vaccinating people in regions with larger populations better suppresses the spread of infection, which turns out to be a part of a general law that the same quantity of vaccines can work efficiently by maximizing the conditional entropy Hc of the distribution of vaccines to regions. This strategy outperformed vaccination in regions with a larger effective regeneration number. These results, understandable through the new concept of social stirring, correspond to the fact that travel activities across regional borders may even suppress the spread of vaccination if processed at a sufficiently high pace. This effect can be further reinforced if vaccines are equally distributed to local regions.
Overview and Discussion of the Competition on Legal Information, Extraction/Entailment (COLIEE) 2023Goebel, Randy; Kano, Yoshinobu; Kim, Mi-Young; Rabelo, Juliano; Satoh, Ken; Yoshioka, Masaharu
doi: 10.1007/s12626-023-00152-0pmid: 38646588
We summarize the 10th Competition on Legal Information Extraction and Entailment. In this tenth edition, the competition included four tasks on case law and statute law. The case law component includes an information retrieval task (Task 1), and the confirmation of an entailment relation between an existing case and a selected unseen case (Task 2). The statute law component includes an information retrieval task (Task 3), and an entailment/question-answering task based on retrieved civil code statutes (Task 4). Participation was open to any group based on any approach. Ten different teams participated in the case law competition tasks, most of them in more than one task. We received results from 8 teams for Task 1 (22 runs) and seven teams for Task 2 (18 runs). On the statute law task, there were 9 different teams participating, most in more than one task. 6 teams submitted a total of 16 runs for Task 3, and 9 teams submitted a total of 26 runs for Task 4. We describe the variety of approaches, our official evaluation, and analysis of our data and submission results.
Data Augmentation and Large Language Model for Legal Case Retrieval and EntailmentBui, Minh-Quan; Do, Dinh-Truong; Le, Nguyen-Khang; Nguyen, Dieu-Hien; Nguyen, Khac-Vu-Hiep; Anh, Trang Pham Ngoc; Le Nguyen, Minh
doi: 10.1007/s12626-024-00158-2pmid: N/A
The Competition on Legal Information Extraction and Entailment (COLIEE) is a well-known international competition organized each year with the goal of applying machine learning algorithms and techniques in the analysis and understanding of legal documents. Two main applications of using machine learning in this domain are entailment and information retrieval. In the realm of legal text analysis, the scarcity of annotated data poses a significant challenge for training robust models. To address this limitation, we employ data augmentation methods to artificially expand the training dataset, enhancing the model’s ability to generalize across diverse legal contexts. Additionally, our approach harnesses the power of a state-of-the-art language model, enabling the extraction of nuanced legal information and improving entailment predictions. We evaluate the performance of our methodology on datasets from the competition, showcasing its effectiveness in achieving competitive results.
Legal Information Retrieval and Entailment Using Transformer-based ApproachesKim, Mi-Young; Rabelo, Juliano; Babiker, Housam Khalifa Bashier; Rahman, Md Abed; Goebel, Randy
doi: 10.1007/s12626-023-00153-zpmid: 38646589
The challenge of information overload in the legal domain increases every day. The COLIEE competition has created four challenge tasks that are intended to encourage the development of systems and methods to alleviate some of that pressure: a case law retrieval (Task 1) and entailment (Task 2), and a statute law retrieval (Task 3) and entailment (Task 4). Here we describe our methods for Task 1 and Task 4. In Task 1, we used a sentence-transformer model to create a numeric representation for each case paragraph. We then created a histogram of the similarities between a query case and a candidate case. The histogram is used to build a binary classifier that decides whether a candidate case should be noticed or not. In Task 4, our approach relies on fine-tuning a pre-trained DeBERTa large language model (LLM) trained on SNLI and MultiNLI datasets. Our method for Task 4 was ranked third among eight participating teams in the COLIEE 2023 competition. For Task 4, We also compared the performance of the DeBERTa model with those of a knowledge distillation model and ensemble methods including Random Forest and Voting.
Contribution Analysis of Large Language Models and Data Augmentations for Person Names in Solving Legal Bar Examination at COLIEE 2023Onaga, Takaaki; Fujita, Masaki; Kano, Yoshinobu
doi: 10.1007/s12626-024-00155-5pmid: N/A
This paper describes our system for COLIEE 2023 Task 4, which automatically answers Japanese legal bar exam problems. We propose an extension to our previous system in COLIEE 2022, which achieved the highest accuracy among all submissions using data augmentation. We focus on problems that include mentions of person names. In this paper, we present two main contributions. First, we incorporate LUKE as our deep learning component, which is a named entity recognition model trained on RoBERTa. Second, we fine-tune the pretrained LUKE model in multiple ways, comparing fine-tuning on training datasets that include alphabetical person names and ensembling different fine-tuning models. We confirmed that LUKE and its fine-tuned model on person type problems improve their accuracies. Our formal run results show that LUKE and our fine-tuning approach using alphabetical person names were effective, achieving an accuracy of 0.69 in the COLIEE 2023 Task 4 formal run.
NOWJ at COLIEE 2023: Multi-task and Ensemble Approaches in Legal Information ProcessingVuong, Thi-Hai-Yen; Nguyen, Hai-Long; Nguyen, Tan-Minh; Nguyen, Hoang-Trung; Nguyen, Thai-Binh; Nguyen, Ha-Thanh
doi: 10.1007/s12626-024-00157-3pmid: N/A
This paper presents the NOWJ team’s approach to the COLIEE 2023 Competition, which focuses on advancing legal information processing techniques and applying them to real-world legal scenarios. Our team tackled the four tasks in the competition, which involved legal case retrieval, legal case entailment, statute law retrieval, and legal textual entailment. We employ state-of-the-art machine learning models and innovative approaches, such as BERT, Longformer, BM25-ranking algorithm, and multi-task learning models. Our participation in the COLIEE 2023 has provided useful insights including the importance of the pre-processing and feature engineering, effectiveness of the multi-task models in combining different legal tasks to improve model’s performance. Although our team did not achieve state-of-the-art results, our findings identify areas for further research and improvements in legal information processing.