Generative AI offers transformative potential for high-stakes domains such as healthcare and finance, yet privacy and regulatory barriers hinder the use of real-world data. To address this, differentially private synthetic data generation has emerged as a promising alternative. In this work, we introduce a unified benchmark to systematically evaluate the utility and fidelity of text datasets generated under formal Differential Privacy (DP) guarantees. Our benchmark addresses key challenges in domain-specific benchmarking, including choice of representative data and realistic privacy budgets, accounting for pre-training and a variety of evaluation metrics. We assess state-of-the-art privacy-preserving generation methods across five domain-specific datasets, revealing significant utility and fidelity degradation compared to real data, especially under strict privacy constraints. These findings underscore the limitations of current approaches, outline the need for advanced privacy-preserving data sharing methods and set a precedent regarding their evaluation in realistic scenarios.

Discontinuous Named Entity Recognition (DNER) presents a challenging problem where entities may be scattered across multiple non-adjacent tokens, making traditional sequence labelling approaches inadequate. Existing methods predominantly rely on custom tagging schemes to handle these discontinuous entities, resulting in models tightly coupled to specific tagging strategies and lacking generalisability across diverse datasets. To address these challenges, we propose TriG-NER, a novel Triplet-Grid Framework that introduces a generalisable approach to learning robust token-level representations for discontinuous entity extraction. Our framework applies triplet loss at the token level, where similarity is defined by word pairs existing within the same entity, effectively pulling together similar and pushing apart dissimilar ones. This approach enhances entity boundary detection and reduces the dependency on specific tagging schemes by focusing on word-pair relationships within a flexible grid structure. We evaluate TriG-NER on three benchmark DNER datasets and demonstrate significant improvements over existing grid-based architectures. These results underscore our framework's effectiveness in capturing complex entity structures and its adaptability to various tagging schemes, setting a new benchmark for discontinuous entity extraction.

The practice of fine-tuning Pre-trained Language Models (PLMs) from general or domain-specific data to a specific task with limited resources, has gained popularity within the field of natural language processing (NLP). In this work, we re-visit this assumption and carry out an investigation in clinical NLP, specifically Named Entity Recognition (NER) on drugs and their related attributes. We compare Transformer models that are trained from scratch to fine-tuned BERT-based Large Language Models (LLMs) namely BERT, BioBERT, and ClinicalBERT. Furthermore, we examine the impact of an additional Conditional Random Field (CRF) layer on such models to encourage contextual learning. We use n2c2-2018 shared task data for model development and evaluations. The experimental outcomes show that 1) CRF layers improved all language models; 2) referring to BIO-strict span level evaluation using macro-average F1 score, although the fine-tuned LLMs achieved 0.83+ scores, the TransformerCRF model trained from scratch achieved 0.78+, demonstrating comparable performances with much lower cost, e.g. with 39.80% less training parameters; 3) referring to BIO-strict span-level evaluation using weighted-average F1 score, ClinicalBERT-CRF, BERT-CRF, and TransformerCRF exhibited lower score differences, with 97.59%/97.44%/96.84% respectively. 4) applying efficient training by down-sampling for better data distribution further reduced the training cost and need for data, while maintaining similar scores -i.e. around 0.02 points lower compared to using the full dataset. This This TRANSFORMERCRF project is hosted at https://github.com/HECTA-UoM/TransformerCRF

Clinical texts, represented in electronic medical records (EMRs), contain rich medical information and are essential for disease prediction, personalised information recommendation, clinical decision support, and medication pattern mining and measurement. Relation extractions between medication mentions and temporal information can further help clinicians better understand the patients’ treatment history. To evaluate the performances of deep learning (DL) and large language models (LLMs) in medication extraction and temporal relations classification, we carry out an empirical investigation of MEDTEM project using several advanced learning structures including BiLSTM-CRF and CNN-BiLSTM for a clinical domain named entity recognition (NER), and BERT-CNN for temporal relation extraction (RE), in addition to the exploration of different word embedding techniques. Furthermore, we also designed a set of post-processing roles to generate structured output on medications and the temporal relation. Our experiments show that CNN-BiLSTM slightly wins the BiLSTM-CRF model on the i2b2-2009 clinical NER task yielding 75.67, 77.83, and 78.17 for precision, recall, and F1 scores using Macro Average. BERT-CNN model also produced reasonable evaluation scores 64.48, 67.17, and 65.03 for P/R/F1 using Macro Avg on the temporal relation extraction test set from i2b2-2012 challenges. Code and Tools from MEDTEM will be hosted at https://github.com/HECTA-UoM/MedTem

Extracting meaningful drug-related information chunks, such as adverse drug events (ADE), is crucial for preventing morbidity and saving many lives. Most ADEs are reported via an unstructured conversation with the medical context, so applying a general entity recognition approach is not sufficient enough. In this paper, we propose a new multi-aspect cross-integration framework for drug entity/event detection by capturing and aligning different context/language/knowledge properties from drug-related documents. We first construct multi-aspect encoders to describe semantic, syntactic, and medical document contextual information by conducting those slot tagging tasks, main drug entity/event detection, part-of-speech tagging, and general medical named entity recognition. Then, each encoder conducts cross-integration with other contextual information in three ways: the key-value cross, attention cross, and feedforward cross, so the multi-encoders are integrated in depth. Our model outperforms all SOTA on two widely used tasks, flat entity detection and discontinuous event extraction.

Traditionally, predictive maintenance of wind turbines has relied on experts to perform time consuming feature pre-processing using statistical, time and frequency domain analysis. Recent advancements in Convolutional Neural Networks have opened the potential for using featureless approaches that learn the discriminating patterns from big data sets without expert intervention. Given multi-dimensional time series data representing sensed electric currents, in this paper we explore the optimal window length that can be used to accurately determine its speed and load using Convolutional and Residual Networks. Choosing an optimal window length is a trade-off between accuracy and number of predictions per second. Fast predictions for operating parameters are useful in maintenance strategies but they come at a cost of decreased accuracy (as there is less data available in a shorter time interval). We show how fusing multiple signals can achieve high accuracy with nine speed and load cases varying from 375rpm with 0% load to 1500rpm and 100% load. Using Class Activation Maps we investigate features in the time domain picked up by the network to make its classification decisions. Further, we train the networks to predict the drive loads in a regression setting where the models are able to generalize well on unseen cases.

The automatic extraction of temporal information from written texts is pivotal for many Natural Language Processing applications such as question answering, text summarisation and information retrieval. It allows to filter information and infer temporal flows of events. This paper presents ManTIME, a general domain temporal expression identification and normalisation system, and systematically explores the impact of different features and training corpora on the performance. The identification phase combines the use of conditional random fields along with a post-processing pipeline, whereas the normalisation phase is carried out using NorMA, an open-source rule-based temporal normaliser. We investigate the performance variation with respect to different feature types. Specifically, we show that the use of WordNet-based features in the identification task negatively affects the overall performance, and that there is no statistically significant difference in the results based on gazetteers, shallow parsing and propositional noun phrases labels on top of the morpho-lexical features. We also show that the use of silver data (alone or in addition to the human-annotated ones) does not improve the performance. We evaluate six combinations of training data and post-processing pipeline with respect to the TempEval-3 benchmark test set. The best run achieved 0.95 (precision), 0.85 (recall) and 0.90 (Fβ=1) in the identification phase. Normalisation accuracies are 0.86 (for type attribute) and 0.77 (for value attribute). The proposed approach ranked 3rd in the TempEval-3 challenge (task A) as the best performing machine learning-based system among 21 participants.