Smart Contracts Auto-generation for Supply Chain Contexts

Identifying and extracting information from contracts is an important task of contract analysis, which is mostly performed manually by lawyers and legal specialists. This manual analysis is a time-consuming, error-prone task. We can overcome this by automating the task of legal entity extraction using the Natural Language Processing (NLP) techniques. For extracting information from the natural language text, we can use popular NLP methods Named Entity Recognition (NER) and relation extraction (RE). Most NER and RE methods rely on machine learning and deep learning to identify relevant entities in natural language text. The main concern in adapting the AI methods for contract element extraction is the scarcity of annotated datasets in the legal field. Aiming at tackling this challenge, we decided to prepare the contract datasets for NER and RE tasks by manually annotating publicly available English contracts. This work is a part of the research aimed at automating the conversion of natural language contracts into Smart Contracts in the blockchain-based Supply Chain context. This paper explains the implementation and comparison of NER models using the deep learning methods BiLSTM and transformer-based BERT for evaluating the dataset.KeywordsDatasetDeep learningLegal domainNLPNERRE

With the development of the global economy and the progress of science and technology, the importance of supply chain management in modern economic activities has become increasingly prominent. However, traditional supply chain management is characterized by problems such as information silos, low transparency, and difficulties in traceability, which seriously affect the efficiency and security of the supply chain. The introduction of blockchain technology provides a new technical path and solution to solve these problems. This paper explores the application of blockchain technology, especially smart contracts, in supply chain management. By developing Python-based smart contracts, this paper verifies the effectiveness of blockchain technology in enhancing supply chain transparency, efficiency, security, and trust. In addition, this paper demonstrates the current status and challenges of the application of blockchain technology in supply chain management through literature review and case study analysis, and points out the direction of future research. The findings of this paper show that the application of blockchain technology in supply chain management has significant advantages, but it is still necessary to further optimize the performance and security of smart contracts and explore more application scenarios.

IntroductionThe labor market is rapidly evolving, leading to a mismatch between existing Knowledge, Skills, and Abilities (KSAs) and future occupational requirements. Reports from organizations like the World Economic Forum and the OECD emphasize the need for dynamic skill identification. This paper introduces a novel system for constructing a dynamic taxonomy using Natural Language Processing (NLP) techniques, specifically Named Entity Recognition (NER) and Relation Extraction (RE), to identify and predict future skills. By leveraging machine learning models, this taxonomy aims to bridge the gap between current skills and future demands, contributing to educational and professional development.MethodsTo achieve this, an NLP-based architecture was developed using a combination of text preprocessing, NER, and RE models. The NER model identifies and categorizes KSAs and occupations from a corpus of labor market reports, while the RE model establishes the relationships between these entities. A custom pipeline was used for PDF text extraction, tokenization, and lemmatization to standardize the data. The models were trained and evaluated using over 1,700 annotated documents, with the training process optimized for both entity recognition and relationship prediction accuracy.ResultsThe NER and RE models demonstrated promising performance. The NER model achieved a best micro-averaged F1-score of 65.38% in identifying occupations, skills, and knowledge entities. The RE model subsequently achieved a best micro-F1 score of 82.2% for accurately classifying semantic relationships between these entities at epoch 1,009. The taxonomy generated from these models effectively identified emerging skills and occupations, offering insights into future workforce requirements. Visualizations of the taxonomy were created using various graph structures, demonstrating its applicability across multiple sectors. The results indicate that this system can dynamically update and adapt to changes in skill demand over time.DiscussionThe dynamic taxonomy model not only provides real-time updates on current competencies but also predicts emerging skill trends, offering a valuable tool for workforce planning. The high recall rates in NER suggest strong entity recognition capabilities, though precision improvements are needed to reduce false positives. Limitations include the need for a larger corpus and sector-specific models. Future work will focus on expanding the corpus, improving model accuracy, and incorporating expert feedback to further refine the taxonomy.

The integration of Natural Language Processing (NLP) into the healthcare domain has revolutionized the way medical information is processed, analyzed, and utilized. With the exponential growth of unstructured data in Electronic Health Records (EHRs), clinical notes, radiology reports, and biomedical literature, NLP provides an effective mechanism to extract, structure, and interpret valuable insights from vast textual datasets. This paper explores the significant role of NLP in medical text analysis and diagnosis support, focusing on its methodologies, applications, and implications for clinical practice. NLP techniques such as Named Entity Recognition (NER), text classification, relation extraction, and semantic analysis enable the identification of key clinical concepts including diseases, medications, symptoms, and treatment patterns. These tools assist in automating administrative tasks, supporting physicians in clinical decision-making, and improving diagnostic accuracy. Furthermore, deep learning models such as BioBERT, ClinicalBERT, and MedRoBERTa have significantly advanced medical NLP applications by providing contextual understanding of domain-specific terminology. The difficulties in implementing NLP in the healthcare industry, such as data protection, interoperability, and model interpretability, are also covered in the study. It illustrates how NLP-based systems might improve patient outcomes, streamline healthcare delivery, and support precision medicine through an analysis of recent research. Highlighting how NLP technology may improve diagnosis assistance, decision-making, and patient-centered care in the contemporary healthcare environment by bridging the gap between unstructured medical data and actionable clinical intelligence is the ultimate goal. Keywords : Natural Language Processing (NLP), Medical Text Analysis, Clinical Decision Support, Named Entity Recognition (NER), Disease Classification, Electronic Health Records (EHR), Transformer Models

Negation-based transfer learning for improving biomedical Named Entity Recognition and Relation Extraction

Cyber threat intelligence (CTI) has been explored to strengthen system security via taking raw threat data from various data sources and transforming it into actionable insights that enable organizations to predict, detect, and respond to cyber threats. Named entity recognition (NER) and relation extraction (RE) are the key tasks of CTI data mining. However, current CTI NER and/or RE research is mainly focused on English CTI, which is not directly transferable to Chinese CTI due to fundamental linguistic and terminological differences. Moreover, the existing limited studies on Chinese CTI do not effectively address uncertainty in predictions in low-resource scenarios where entities and relations are sparse. This work aims to improve the performance of NER and RE tasks in low-resource Chinese CTI scenarios, and we make two major contributions. The first is that we construct a Chinese CTI dataset, which includes 16 types of entities and 9 types of relations—more than those of the existing open-source dataset on Chinese CTI. The second is that we propose an entropy-driven approach for entity and relation (EDAER) extraction. EDAER is the first to combine the techniques of RoBERTa_wwm, Mamba, RDCNN and CRF to perform NER tasks. In addition, EDAER is the first to apply entropy to quantify the uncertainty of the model’s predictions in NER and RE tasks in Chinese CTI scenarios. Moreover, EDAER is the first to apply contrastive learning techniques in Chinese CTI scenarios to learn meaningful features by maximizing the similarity between positive samples and minimizing the similarity between negative samples. Extensive experimental results on public and our built datasets demonstrate that our proposed approach performs the best. These results show that (1) RoBERTa_wwwm significantly outperforms BERT on both NER and RE tasks; (2) Mamba outperforms BiLSTM on the NER task; (3) the entropy-based dynamic gating mechanism contributes to performance improvements in both NER and RE tasks; and (4) the uncertainty-guided contrastive learning mechanism is helpful for performance improvement in the NER task.

The cybersecurity of contemporary systems has drawn much more focus from both academic and industrial viewpoints. The blockchain-based approach has recently become more popular due to how straightforward it is, especially in the management of supply chains. This highlights how crucial the quality factors are from a supply chain management standpoint. Numerous sectors have come to realize how crucial it is to have reliable supply chain and logistics solutions. The introduction of blockchain technology has given rise to several possible breakthroughs in the management and monitoring of corporate operations, specifically supply chain procedures. The blockchain and, more precisely, a smart contract technology that was utilized to manage the process of creating, verifying, and inspecting data over the supply chain management process were both discussed in this study. Next, discuss blockchain cybersecurity in the context of supply chains. Security protection needs to be powerful sufficient to shield the assets and data from dangers, as the smart contract increasingly controls the movement of data over many places. The paper then examines the primary security breaches that have an impact on the data on the blockchain and offers a fix.

Current research on smart contracts focuses on technical, conceptual, and legal aspects but neglects organizational requirements and sustainability impacts. We consider this a significant research gap and explore the relationship between smart contracts and sustainability in supply chains. First, we define the concept of smart contracts in terms of supply chain management. Then, we conduct a content analysis of the literature to explore the overlapping research fields of smart contracts and sustainability in supply chains. Next, we develop a semi-structured assessment framework to model the potential environmental and social impacts induced by smart contracts on supply chains. We propose a conceptual framework for supply chain maturity by mapping the relationships between organizational development, sustainability, and technology. We identify smart contracts as a foundational technology that enables efficient and transparent governance and collaborative self-coordination of human and non-human actors. Thus, we argue that smart contracts can contribute to the economic and social development of networked value chains and Society 5.0. To stimulate interdisciplinary research on smart contracts, we conclude the article by formulating research propositions and trade-offs for smart contracts in the context of technology development, business process and supply chain management, and sustainability.

Biomedical relation extraction from scientific publications is a key task in biomedical natural language processing (NLP) and can facilitate the creation of large knowledge bases, enable more efficient knowledge discovery, and accelerate evidence synthesis. In this paper, building upon our previous effort in the BioCreative VIII BioRED Track, we propose an enhanced end-to-end pipeline approach for biomedical relation extraction (RE) and novelty detection (ND) that effectively leverages existing datasets and integrates state-of-the-art deep learning methods. Our pipeline consists of four tasks performed sequentially: named entity recognition (NER), entity linking (EL), RE, and ND. We trained models using the BioRED benchmark corpus that was the basis of the shared task. We explored several methods for each task and combinations thereof: for NER, we compared a BERT-based sequence labeling model that uses the BIO scheme with a span classification model. For EL, we trained a convolutional neural network model for diseases and chemicals and used an existing tool, PubTator 3.0, for mapping other entity types. For RE and ND, we adapted the BERT-based, sentence-bound PURE model to bidirectional and document-level extraction. We also performed extensive hyperparameter tuning to improve model performance. We obtained our best performance using BERT-based models for NER, RE, and ND, and the hybrid approach for EL. Our enhanced and optimized pipeline showed substantial improvement compared to our shared task submission, NER: 93.53 (+3.09), EL: 83.87 (+9.73), RE: 46.18 (+15.67), and ND: 38.86 (+14.9). While the performances of the NER and EL models are reasonably high, RE and ND tasks remain challenging at the document level. Further enhancements to the dataset could enable more accurate and useful models for practical use. We provide our models and code at https://github.com/janinaj/e2eBioMedRE/. Database URL: https://github.com/janinaj/e2eBioMedRE/.

Scientific growth is iterative, with existing knowledge serving as the foundation for new discoveries. Citations serve as the primary channel for information propagation in science, shaping which ideas and findings persist in the literature and which do not. While natural language processing (NLP) is increasingly used in citation context analysis, it is underutilized in studies that examine the actual scientific content of citations. In this pilot study, we explored how NLP can be used to track the propagation of scientific findings by replicating a prior citation context study that relied on manual extraction. We compared two approaches: a traditional NLP pipeline (named entity recognition and relation extraction) and a generative large language model (LLM). We formulated a two-step automated pipeline: (1) extracting findings from a reference paper and (2) mapping citation contexts to the findings they reference. Our findings indicate that LLMs are superior to traditional NLP techniques in both steps of the pipeline. However, they are also more prone to errors, mapping citation contexts to findings they do not reference. While the two-step automated pipeline was effective, integrating manual annotation of findings with LLM-based mapping of citation contexts yields the best results. To our knowledge, this study is one of the first to explore how NLP, particularly LLMs, can be leveraged to track the flow of information in science. Future research should further evaluate the application of LLMs and other NLP techniques on a larger scale to assess their effectiveness in supporting citation-focused scientometric and informetric studies.

Automatically extracting geographic information from text is the key to harnessing the vast amount of spatial knowledge that only exists in this unstructured form. The fundamental elements of spatial knowledge include spatial entities, their types and the spatial relations between them. Structuring the spatial knowledge contained within text as a geospatial knowledge graph, and disambiguating the spatial entities, significantly facilitates its reuse. The automatic extraction of geographic information from text also allows the creation or enrichment of gazetteers. We propose a baseline approach for nested spatial entity and binary spatial relation extraction from text, a new annotated French-language benchmark dataset on the maritime domain that can be used to train algorithms for both extraction tasks, and benchmark results for the two tasks carried out individually and end-to-end. Our approach involves applying the Princeton University Relation Extraction system (PURE), made for flat, generic entity extraction and generic binary relation extraction, to the extraction of nested, spatial entities and spatial binary relations. By extracting nested spatial entities and the spatial relations between them, we have more information to aid entity disambiguation. In our experiments we compare the performance of a pretrained monolingual French BERT language model with that of a pretrained multilingual BERT language model, and study the effect of including cross-sentence context. Our results reveal very similar results for both models, although the multilingual model performs slightly better in entity extraction, and the monolingual model has slightly better relation extraction and end-to-end performances. We observe that increasing the amount of cross-sentence context improves the results for entity extraction whereas it has the opposite effect on relation extraction.

The extraction of entities and relations from unstructured clinical records has been attracting increasing attention. In addition to the existing traditional methods, deep learning methods have also been proposed for entity and relation extraction. However, previous work on clinical entity and relation extraction did not consider the multiple relations between clinical entities, which often exist in clinical texts. To deal with multiple relations, we propose using a multi-head selection method for clinical entity and relation extraction. As pre-trained language models have been shown to be effective for clinical entity and relation extraction, we integrate a pre-trained language model with a multi-head model to jointly extract clinical entities and relations. The experimental results show that the proposed model is effective for entity and relation extraction on both the i2b2/VA 2010 and n2c2 2018 challenge datasets and outperforms the top-ranking systems in the n2c2 2018 challenge. We also evaluate the impact of four existing pre-trained language models on clinical entity and relation extraction performance. The domain-specific pre-trained language model improves the performance of clinical entity and relation extraction. Between BERT and CharacterBERT, which uses a Character-CNN module instead of BERT's wordpiece system to represent entire words, we find that BERT outperforms CharacterBERT on joint extraction of clinical entities and relations.

In today's globalised economy, comprehensive supply chain visibility is crucial for effective risk management. Achieving visibility remains a significant challenge due to limited information sharing among supply chain partners. This paper presents a novel framework leveraging Knowledge Graphs (KGs) and Large Language Models (LLMs) to enhance supply chain visibility, without direct reliance on stakeholder information sharing. Our zero-shot, LLM-driven framework enables the automated extraction of diverse and domain-specific supply chain information from publicly available sources, and constructs structured knowledge graphs that capture complex, multi-tier interdependencies across supply chain entities, geographic locations, ownership structures, and product flows. We employ zero-shot prompting for Named Entity Recognition (NER) and Relation Extraction (RE) tasks, eliminating the need for extensive domain-specific training. We validate the framework through both quantitative evaluations and a case study on EV supply chains, specifically focussing on tracking critical minerals for battery manufacturing. The results demonstrates the effectiveness of the framework in supply chain mapping, which extends visibility beyond tier-2 suppliers. Additionally, the framework reveals critical dependencies and alternative sourcing options, enhancing risk management and strategic planning in case of disruptions. With high precision in NER and RE tasks, it provides an effective tool for understanding complex, multi-tiered supply networks. This research offers a novel framework for constructing domain-specific supply chain knowledge graphs, addressing longstanding challenges in visibility and paving the way for advancements in digital supply chain surveillance.

This paper investigates the potential of integrating supply chain management with blockchain technology, specifically by implementing smart contracts on the Ethereum network using Solidity. The paper explores supply chain management concepts, blockchain, distributed ledger technology, and smart contracts in the context of their integration into supply chains to increase traceability, transparency, and accountability with faster processing times. After investigating these technologies’ applications and potential use cases, a framework for smart contract implementation for supply chain management is constructed. Potential data models and functions of a smart contract implementation improving supply chain management processes are discussed. After constructing a framework, the effects of the proposed system on supply chain processes are explained. The proposed framework increases the reliability of the supply chain history due to the usage of DLT (distributed ledger technology). It utilizes smart contracts to increase the manageability and traceability of the supply chain. The proposed framework also eliminates the SPoF (Single Point of Failure) vulnerabilities and external alteration of the transactional data. However, due to the ever-changing and variable nature of the supply chains, the proposed architecture might not be a one-size-fits-all solution, and tailor-made solutions might be necessary for different supply chain management implementations.

Supply Chain Management, Blockchains and Smart Contracts