Abstract
For seven years, the Text2Story Workshop series has fostered a vibrant community dedicated to understanding narrative structure in text, resulting in significant contributions to the field and developing a shared understanding of the challenges in this domain. While traditional methods have yielded valuable insights, the advent of Transformers and LLMs have ignited a new wave of interest in narrative understanding. The previous iteration of the workshop also witnessed a surge in LLM-based approaches, demonstrating the community’s growing recognition of their potential. In this eighth edition we propose to go deeper into the role of LLMs in narrative understanding. While LLMs have revolutionized the field of NLP and are the go-to tools for any NLP task, the ability to capture, represent and analyze contextual nuances in longer texts is still an elusive goal, let alone the understanding of consistent fine-grained narrative structures in text. Consequently, this iteration of the workshop will explore the issues involved in using LLMs to unravel narrative structures, while also examining the characteristics of narratives generated by LLMs. By fostering dialogue on these emerging areas, we aim to continue the workshop's tradition of driving innovation in narrative understanding research. Text2Story encompasses sessions covering full research papers, work-in-progress, demos, resources, position and dissemination papers, along with one keynote talk. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
Recent advances in natural language processing have raised expectations for generative models to produce coherent text across diverse language varieties. In the particular case of the Portuguese language, the predominance of Brazilian Portuguese corpora online introduces linguistic biases in these models, limiting their applicability outside of Brazil. To address this gap and promote the creation of European Portuguese resources, we developed a cross-domain language variety identifier (LVI) to discriminate between European and Brazilian Portuguese. Motivated by the findings of our literature review, we compiled the PtBrVarId corpus, a cross-domain LVI dataset, and study the effectiveness of transformer-based LVI classifiers for cross-domain scenarios. Although this research focuses on two Portuguese varieties, our contribution can be extended to other varieties and languages. We open source the code, corpus, and models to foster further research in this task.

Abstract
Language models have become foundational to many widely used systems. However, these seemingly advantageous models are double-edged swords. While they excel in tasks related to resource-rich languages like English, they often lose the fine nuances of language forms, dialects, and varieties that are inherent to languages spoken in multiple regions of the world. Languages like European Portuguese are neglected in favor of their more popular counterpart, Brazilian Portuguese, leading to suboptimal performance in various linguistic tasks. To address this gap, we introduce the first open-source translation model specifically tailored for European Portuguese, along with a novel dataset specifically designed for this task. Results from automatic evaluations on two benchmark datasets demonstrate that our best model surpasses existing open-source translation systems for Portuguese and approaches the performance of industry-leading closed-source systems for European Portuguese. By making our dataset, models, and code publicly available, we aim to support and encourage further research, fostering advancements in the representation of underrepresented language varieties.

Abstract
This study investigates spatial distribution and chemical elemental composition screening in soils in Rome (Italy) using X-ray fluorescence analysis. Fifty-nine soil samples were collected from various locations within the urban areas of the Rome municipality and were analyzed for 19 elements. Multivariate statistical techniques, including nonlinear mapping, principal component analysis, and hierarchical cluster analysis, were employed to identify clusters of similar soil samples and their spatial distribution and to try to obtain environmental quality information. The soil sample clusters result from natural geological processes and anthropogenic activities on soil contamination patterns. Spatial clustering using the k-means algorithm further identified six distinct clusters, each with specific geographical distributions and elemental characteristics. Hence, the findings underscore the importance of targeted soil assessments to ensure the sustainable use of land resources in urban areas.

Abstract
In healthcare, diagnoses usually rely on physician expertise. However, complex cases may benefit from consulting similar past clinical reports cases. In this paper, we present MedLink (http://medlink.inesctec.pt), a tool that given a free-text medical report, retrieves and ranks relevant clinical case reports published in health conferences and journals, aiming to support clinical decision-making, particularly in challenging or complex diagnoses. To this regard, we trained two BERT models on the sentence similarity task: a bi-encoder for retrieval and a cross-encoder for reranking. To evaluate our approach, we used 10 medical reports and asked a physician to rank the top 10 most relevant published case reports for each one. Our results show that MedLink’s ranking model achieved NDCG@10 of 0.747. Our demo also includes the visualization of clinical entities (using a NER model) and the production of a textual explanation (using a LLM) to ease comparison and contrasting between reports. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
Detecting anomalies in Waste transportation networks is vital for uncovering illegal or unsafe activities, that can have serious environmental and regulatory consequences. Identifying anomalies in such networks presents a significant challenge due to the limited availability of labeled data and the subtle nature of illicit activities. Moreover, traditional anomaly detection methods relying solely on individual transaction data may overlook deeper, network-level irregularities that arise from complex interactions between entities, especially in the absence of labeled data. This study explores anomaly detection in a waste transport network using unsupervised learning, enhanced by limited supervision and enriched with network structure information. Initially, unsupervised models like Isolation Forest, K-Means, LOF, and Autoencoders were applied using statistical and graph-based features. These models detected outliers without prior labels. Later, information on a few confirmed anomalous users enabled weak supervision, guiding feature selection through statistical tests like Kolmogorov-Smirnov and Anderson-Darling. Results show that models trained on a reduced, graph-focused feature set improved anomaly detection, particularly under extreme class imbalance. Isolation Forest notably ranked known anomalies highly. Ego network visualizations supported these findings, demonstrating the value of integrating structural features and limited labels for identifying subtle, relational anomalies.