Search Results (498)

Historical document collections are increasingly available as digitised images and PDFs, but their conversion into reliable text remains affected by optical character recognition (OCR) errors, degraded pages, heterogeneous layouts, and domain-specific terminology. This study proposes a pathway-level framework for documenting and comparing conventional OCR, OCR followed by large language model (LLM)-assisted correction, and direct multimodal transcription. The framework is demonstrated using the Portuguese Agricultural and Forestry Surveys (1950–1958). A stratified validation sample of 45 pages was selected by visual quality, page type, and geographic coverage. Outputs were evaluated against manually verified reference transcriptions using content-normalised character error rate (CER) and word error rate (WER), document-condition analysis, paired statistical tests, and an entity-level semantic preservation assessment focused on place names, agricultural terms, and measurement expressions. Under the evaluated model and interface conditions, both LLM-based pathways produced lower mean CER and WER than the conventional OCR baseline, with the lowest values observed for direct multimodal transcription. Semantic preservation was also higher for the LLM-based pathways, although measurement expressions remained the most persistent risk, particularly in table-based pages. Downstream tasks were not directly evaluated. The findings support the framework as a method for validating text-extraction pathways before reuse, rather than establishing a universal ranking of tools. Full article

Industrial maintenance and fault-diagnosis systems generate textual records, such as maintenance work orders, service requests, causal analyses, and troubleshooting solutions. These records contain domain-specific named entities that provide valuable knowledge for intelligent monitoring, fault diagnosis, maintenance decision support, and industrial knowledge graph construction. However, in practical industrial environments, maintenance records are strongly associated with specific equipment types, production processes, fault modes, and enterprise-specific terminology. As a result, entity schemas vary across systems, new entity types emerge with equipment updates, and high-quality annotation requires substantial domain expertise. These factors make it difficult to obtain sufficient labeled samples for each industrial entity type. Under such low-resource conditions, conventional supervised named entity recognition (NER) models tend to suffer from unstable entity boundary detection and biased entity representations. To address these challenges, this paper proposes a boundary-aware knowledge graph-guided adaptive prototype correction framework for few-shot NER in industrial maintenance information systems. The proposed framework first introduces a boundary-aware span detection mechanism to improve entity localization in noisy and irregular maintenance texts. A knowledge graph-guided adaptive prototype correction module is then designed to construct entity class prototypes from limited support examples, reducing prototype bias caused by sparse annotations. Experiments are conducted on two representative industrial datasets, MaintIE and CFDK, covering maintenance short texts and fault-diagnosis records. Experimental results show that the proposed framework achieves an average Micro-F1 improvement of 1.89 percentage points over the strongest compared baseline across 12 episodic settings on the two industrial datasets: three MaintIE coarse-grained settings, six MaintIE fine-grained settings, and three CFDK settings. The ablation and sensitivity analyses further indicate that boundary-aware span modeling and KG-guided prototype correction jointly contribute to low-resource entity classification. This study provides a data-efficient information extraction solution for AI-enabled industrial knowledge acquisition, fault diagnosis, and maintenance decision support. Full article

Background: Removing explicit protected health information (PHI) does not necessarily make a clinical narrative non-identifiable. Rare diagnoses, social circumstances, locations, temporal patterns, and treatment trajectories may still permit re-identification. Methods: This PRISMA-ScR-informed scoping review combined PubMed/MEDLINE, OpenAlex, and targeted NLP searches with OpenAlex title-and-abstract, Web of Science, and Scopus sensitivity checks. Eligible publications addressed clinical or biomedical text de-identification from 1 January 2018 to 31 March 2026. Results: The searches yielded 275 records and 258 unique records after deduplication. Eligibility assessment produced 110 core records, 11 background or review records, and 22 exclusions. All 143 eligibility-stage records underwent independent double screening and reconciliation; structured extraction covered all 110 core records. Abstract screening of 47 additional Scopus candidates found no task function or implementation paradigm outside the proposed classification. The resulting two-axis framework separates a method’s role in the workflow from its technical implementation. Conclusions: Clinical text de-identification cannot be reduced to named-entity recognition. Local hybrid or transformer pipelines remain the most defensible baseline for routine PHI detection. LLMs are better suited to defined tasks in augmentation, transformation, and assurance, with local validation and explicit control of data exposure. Full article

Automated compliance checking for building fire protection design requires accurate extraction of domain-specific entities from technical code provisions. However, building fire protection codes contain highly specialized terminology, hierarchical clause structures, and complex regulatory semantics, which make manual information extraction time-consuming and error-prone. This study develops a domain-specific named entity recognition approach for Chinese building fire protection design codes. An expert-annotated dataset was constructed from five representative codes, containing 2748 annotated provisions and 13,877 entity mentions across nine entity categories. A RoBERTa-BiLSTM-CRF model was then developed to capture contextual semantic representations, bidirectional sequence dependencies, and label-transition constraints. Results suggest that the proposed model achieves 88.34%, 88.31%, and 88.32% for precision, recall, and F1-score, respectively. The extracted entities can be organized into structured and traceable records, providing a foundation for downstream building fire protection knowledge management and automated compliance checking. Full article

Extracting composition expressions from materials science patent documents is essential for patent document searches. Composition expressions describing a single unit of elements and quantities (e.g., “Al: 0.02% or more and 0.08% or less”) tend to appear clustered together. In such cases, researchers in the field of materials science who conduct patent searches have found that boundary-indicating phrases are effective for searching. However, there are no concrete examples that have implemented this approach, and the validity of this approach has not been evaluated to date. In this paper, we propose a Separator Tag (SEP-tag) framework as an explicit boundary for composition expressions in named entity recognition labels. This allows the named entity recognition model to simultaneously perform entity recognition and pattern boundary learning within a single end-to-end process. Furthermore, we propose a four-axis evaluation framework that extends the conventional single-entity F1 score to evaluate named entity recognition models using SEP-tags. (1) Entity F1 score excluding structural tags, (2) Exact match rate for correct spans, (3) Predicted span pattern extraction F1 score, (4) Pattern extraction F1 score. We conducted evaluations using RoBERTa-base and BERT-base-Japanese on materials science patent datasets in English (10,166 sentences) and Japanese (975 sentences). Experimental results show that training the model with SEP-tags improved the span exact match rate on the English dataset by approximately 59.72 percentage points (from 15.95% to 75.67%), and reduced false positives in pattern extraction to 1/117 (F1 score: 0.0784 → 0.8503). In the Japanese dataset, false positives were reduced to 1/123 (F1 score: 0.0361 → 0.4877). For both languages, the entity F1 score was equivalent to that of the model without SEP-tags (English: $|\Delta \mathrm{F}1|<0.002$, Japanese: $|\Delta \mathrm{F}1|<0.001$), with no significant difference found for any of the 13 labels. These results demonstrate that explicit structural boundary tokens are highly effective for extracting composition expression patterns in domain-specific named entity recognition. Full article

When people recount personal memories, they often refer to people, places, and events indirectly, relying on contextual cues rather than explicit names. Such implicit references are central to reminiscence narratives: first-person accounts of lived experience used in therapeutic, archival, and social settings. They pose a difficult computational problem because the intended entity must be inferred from dispersed narrative evidence rather than from a local mention. We introduce IRC-Bench, the Implicit Reminiscence Context Benchmark, for evaluating implicit entity recognition in reminiscence transcripts. The benchmark targets non-locality: entity-identifying cues are distributed across multiple, non-contiguous clauses, unlike named entity recognition, entity linking, or coreference resolution. IRC-Bench comprises 25,136 samples constructed from 12,337 Wikidata-linked entities across 1994 transcripts spanning 11 thematic domains. Each sample pairs an Entity-Grounded Narrative, in which the target entity is explicitly mentioned, with an Entity-Elided Narrative, in which direct mentions are removed. We evaluate 19 configurations across LLM generation, dense retrieval, RAG, and fine-tuning. QLoRA-adapted Llama 3.1 8B performs best in the open-world setting (38.94% exact match; 51.59% Jaccard), while fine-tuned DPR leads in closed-world retrieval (35.38% Hit@1; 71.49% Hit@10). We release IRC-Bench with data, code, and evaluation tools. Full article

The growing adoption of context-aware reasoning in Large Language Model (LLM)-based applications, particularly through retrieval-augmented and prompt-enriched architectures, has substantially broadened the utility of LLMs in specialized, real-world scenarios. Yet this progress comes with an underexplored vulnerability: users must supply sensitive contextual information as part of the reasoning process, exposing private data to external LLM service providers and raising serious concerns about informational self-determination. Existing privacy-preserving approaches in NLP are largely ill-suited to this setting, as they either degrade reasoning quality unacceptably or fail to provide formal privacy guarantees. This paper addresses this gap by introducing Textual Differential Privacy (TDP), a principled framework that embeds differential privacy guarantees directly into the textual context supplied to LLMs, enabling privacy-preserving reasoning without sacrificing the semantic coherence that models depend upon. Central to the framework is a Differential Embedding Substitution mechanism, which perturbs sensitive entities in the input space while preserving the structural and semantic properties necessary for downstream reasoning tasks. The framework further introduces a formal privacy loss quantification scheme, providing practitioners with interpretable metrics to navigate the privacy–utility trade-off in deployment. We prove that the mechanism, instantiated as an exponential mechanism over a semantically constrained candidate set, satisfies metric differential privacy with a privacy budget that scales with the cosine distance between entities, and empirical evaluation across context-aware reasoning benchmarks validates its practical effectiveness. By treating privacy as a first-class design principle in LLM-based architectures, this work contributes toward a more trustworthy and broadly deployable foundation for intelligent, context-sensitive AI systems. Full article

Nested named entity recognition (Nested NER) aims to identify and classify all possible span entities within a text. Existing approaches primarily rely on enumeration techniques and span-based methods to address the challenge of overlapping entities. However, these methods often overlook the structural distribution and inherent semantics of entities, making them susceptible to issues such as ambiguous start-end tokens, blurred entity boundaries, and a high degree of token overlap. In this paper, we propose a novel strategy we name Augmented Disentanglement and Aggregation for Nested Named Entity Recognition (ada-NER), which employs a series of augmentation strategies to extract nested entities from text. Specifically, we first reformulate the nested NER task as a problem of disentangling and aggregating the relationships between span recognition and type classification. This formulation enables the model to capture fine-grained and comprehensive contextual interactions within sentences. Furthermore, span entities are recognized through the joint modeling of hard boundary encoding and soft edge encoding, while type classification is enhanced by incorporating both intra and inter distribution relationships as well as dependency information. Finally, we introduce a well-designed fusion mechanism to obtain entity representation within a shared space. Extensive experiments on two public datasets demonstrate the effectiveness of our proposed model, which consistently outperforms competitive baseline methods. Full article

Background: Lung cancer causes more deaths than any other malignancy worldwide, accounting for 2.2 million new cases and 1.8 million deaths in 2020. Extracting structured clinical knowledge from unstructured French-language oncology records remains methodologically unresolved in Tunisian and Francophone healthcare systems, where validated natural language processing tools do not yet exist. This study examined the effectiveness of transformer-based named-entity recognition for automated clinical annotation of Tunisian lung cancer reports. Aim: The study aimed to (i) establish performance baselines for four transformer-based models on a publicly available thoracic radiology dataset, (ii) evaluate five models, including a French biomedical specialist, on a newly constructed Tunisian clinical corpus, and (iii) demonstrate prototype deployment feasibility for structured clinical decision support. Methods: An initial comparative study evaluated BERT, RoBERTa, BioClinicalBERT, and CamemBERT using the official RadGraph dataset partitions, which natively comprise a total of 600 annotated thoracic radiology reports distributed across a standardized 80/10/10 split. Subsequently, five models were evaluated on 200 manually annotated diagnostic reports from Mami Pneumo-Phthisiology Hospital, Tunis. For the Tunisian corpus, a five-fold cross-validation approach was implemented to ensure robust performance estimation, followed by final evaluation on a dedicated hold-out test set. All models were trained for a maximum of 10 epochs, with a learning rate of 5 × 10⁻⁵ and a batch size of 16. Results: Based on the initial comparative study on the RadGraph dataset, where RoBERTa was the top performer and achieved the highest F1-score of 0.873 (precision: 0.869, recall: 0.877), we evaluated its specialized biomedical variant, DR-BERT, on our Tunisian clinical dataset. DR-BERT demonstrated strong generalization on the hold-out test set with an F1-score of 0.824, outperforming the baseline RoBERTa (test F1: 0.791) and showing competitive performance relative to multilingual BERT (0.843 ± 0.005 in five-fold cross-validation). A prototype interface generated structured clinical summaries encompassing prior conditions, imaging modalities, and TNM staging. Conclusion: Language- and domain-adapted transformer models effectively extract structured clinical entities from French-language Tunisian lung cancer reports. DR-BERT’s superior generalization on unseen data confirms that biomedical pretraining in the target language is a key driver of robust performance in specialized French oncology text. This work establishes foundational infrastructure for NLP-driven oncology data management in Tunisia and comparable Francophone settings. Full article

Multimodal named entity recognition (MNER) aims to improve entity detection in social media texts by leveraging accompanying images, but its performance is often affected by weak text–image alignment, noisy or irrelevant visual content, and limited separation among entity representations. To address these issues, this study proposes CUA-MNER, a contrastive uncertainty–aware framework that combines hierarchical vision–text alignment, variational uncertainty–aware fusion, and token-level contrastive learning. The alignment module models correspondences at token, phrase, and sentence levels, allowing local visual regions and global image context to support textual entity recognition. The fusion module estimates epistemic and aleatoric uncertainty through variational inference and adaptively adjusts the contribution of each modality for different samples. The contrastive objective further encourages entity representations of the same type to be closer while separating different entity types. Experiments on the Twitter2015 and Twitter2017 benchmarks demonstrate that CUA-MNER achieves F1 scores of 76.97% and 89.66%, respectively, outperforming competitive baselines by 0.66 and 1.95 F1 points. Ablation and diagnostic analyses show that the three components provide complementary benefits. These results suggest that modeling modality reliability is useful for robust MNER, while the additional modules also introduce computational overhead and leave cross-domain generalization as an open issue. Full article

The increasing complexity and volume of technical documentation, including requirements specifications, patents, and engineering reports, create significant challenges for manual analysis and knowledge extraction. This paper includes a systematic review of methods for semantic content analysis of technical documents, with a particular focus on Natural Language Processing (NLP) techniques and Transformer-based models. The study formalizes the task of structured information extraction and provides a mathematical description of Named Entity Recognition (NER) as a core subtask. A practical case study demonstrates an end-to-end NER pipeline for Russian-language technical requirements, leveraging ruRoberta-large via spaCy-transformers. The results highlight both the potential and limitations of current approaches, emphasizing the critical role of annotation consistency and document format normalization. This work contributes to the development of intelligent systems for engineering documentation analysis and outlines key directions for future research. Full article

Metallurgical lifting equipment operates under prolonged heavy-load, high-impact, and complex working conditions. The resulting failure reports contain rich field knowledge applicable to fault diagnosis and predictive maintenance. Nevertheless, reliably extracting traceable, structured knowledge from procedural and implicit maintenance records remains a significant challenge. To address this, the paper proposes a generative information extraction method for large language models (LLMs) that integrates ontology schema with inference chain constraints, targeting knowledge extraction and knowledge graph construction from failure reports of metallurgical lifting equipment, named generative constrained information extraction for operations and maintenance (GCIE-OM). A domain ontology schema is first constructed, defining seven entity types and nine relation types to establish explicit knowledge boundaries for structured LLM generation. An inference chain-assisted structured parsing method, termed IC-ASP, is then designed to guide the model through a sequential extraction pipeline comprising scene identification, scope of entity boundary, inference of relation type, evidence traceability with localization, and triple output. This stepwise process strengthens the model’s capacity to comprehend equipment hierarchies, fault evolution chains, and maintenance action logic. Building on this, ChatGLM or LLaMA serves as the backbone model and is adapted to the target domain via LoRA fine-tuning. Entity alignment and character-level source localization mechanisms are further introduced to establish precise mappings between generated outputs and their textual evidence in the source documents. The extracted results are ultimately converted into standardized knowledge triples and stored in a Neo4j graph database. Based on this, a prototype system for generative information extraction is designed and implemented to demonstrate the practical effectiveness and adaptability of the proposed method. Experimental results show that the proposed method outperforms baseline methods across entity recognition, relation extraction, and structured output quality, providing robust knowledge support for fault tracing and predictive maintenance of metallurgical lifting equipment. Full article

Despite recent advances, medical question answering systems still struggle with domain-specific reasoning and data efficiency. This paper presents Med-LLaMA3, a family of medical large language models developed by parameter-efficient fine-tuning of the LLaMA-3.1 (8 billion) and LLaMA-3.2 (1 and 3 billion) architectures using quantized low-rank adaptation (QLoRA) and low-rank adaptation (LoRA) with 4-bit quantization. Beyond model training, this work contributes the following: (1) a formalized dataset curation taxonomy (source type × clinical granularity × task format) with a source-category ablation confirming that the multi-source combination drives benchmark gains beyond any single category; (2) a systematic characterization of low-rank-adaptation rank-scaling behavior for the LLaMA-3 family in the medical domain (monotonic improvement up to rank 128, with no observed plateau); and (3) statistically validated comparisons using McNemar’s test and 95% bootstrap confidence intervals. We curated a medical instruction dataset of over 1.5 million samples spanning medical examinations, clinical dialogues, and biomedical literature. Our approach trains only ∼4% of the base model’s parameters and, consistent with prior studies of parameter-efficient methods in the medical domain, achieves performance comparable to full fine-tuning at a fraction of the memory footprint. Evaluated with five in-context examples per prompt, the 8-billion-parameter model attains a mean accuracy of 75.71% across the eight medical-domain subsets of the Massive Multitask Language Understanding benchmark; improvements over the unmodified LLaMA-3.1-8B-Instruct baseline are statistically significant on the medical multiple-choice benchmark MedMCQA and, after Bonferroni correction across the eight subsets, on three subsets (Clinical Knowledge, Medical Genetics, and Nutrition), with two further subsets being significant only before correction. A structured named-entity-recognition evaluation on 100 hospital discharge summaries (macro-averaged F1 0.94; dual-annotator agreement $\kappa =0.87$) provides complementary evidence of clinical-text utility. A safety mitigation pilot shows that context-disambiguation preprocessing reduces the highest-severity abbreviation-ambiguity error rate from 30% to 10% on a 30-case held-out set. These results show that parameter-efficient fine-tuning can deliver high-performance medical large language models while training only ∼4% of the model’s parameters and reducing memory use by roughly 75%, enabling development on low-cost consumer-grade hardware. Full article

Relation extraction is an important task for structuring information from unstructured text. However, the Romanian language still lacks dedicated datasets and benchmarks for this task. To address this gap, we introduce RoRED, a Romanian relation extraction dataset built by combining two complementary data construction strategies: translating existing high-quality English resources and applying distant supervision to native Romanian Wikipedia data. We leverage a powerful open-source large language model to automatically translate English examples into Romanian. For the native subset, we align Romanian Wikipedia entities with Wikidata relations to obtain naturally occurring Romanian examples. To better reflect real-world relation extraction scenarios, we also introduce synthetic negative examples generated using existing Romanian named entity recognition models. Finally, we validate the dataset by fine-tuning and evaluating multiple baseline models. Our strongest model, LUKE-RoRED, achieves a macro-F1 score of $0.8744$ on the RoRED test set, demonstrating that the dataset can support relation extraction for Romanian. Overall, RoRED provides a strong first native benchmark for Romanian relation extraction. Full article

Tea pest and disease named entity recognition (NER) faces challenges resulting from dense domain terminology, multi-granularity entity structures, and long-distance semantic dependencies. This paper proposes E-BERT-wwm-BiGRU-RAT-CRF, integrating whole-word masking E-BERT with three innovations—a trainable relative position bias matrix, a cross-layer hierarchical mask matrix, and a heterogeneous multi-head attention mechanism—followed by bidirectional gated recurrent units (BiGRU), residual attention (RAT), and conditional random fields (CRF). On a self-constructed tea pest and disease corpus of over 300,000 characters across seven entity categories, the model achieves 93.67% precision, 93.07% recall, and 93.37% F1-score, outperforming the baseline by 2.73 percentage points in F1-score. Ablation experiments confirm the contribution of each module. Full article