Abstract
City council minutes are typically lengthy and formal documents with a bureaucratic writing style. Although publicly available, their structure often makes it difficult for citizens or journalists to efficiently find information. In this demo, we present CitiLink, a platform designed to transform unstructured municipal meeting minutes into structured and searchable data, demonstrating how NLP and IR can enhance the accessibility and transparency of local government. The system employs LLMs to extract metadata, discussed subjects, and voting outcomes, which are then indexed in a database to support full-text search with BM25 ranking and faceted filtering through a user-friendly interface. The developed system was built over a collection of 120 min made available by six Portuguese municipalities. To assess its usability, CitiLink was tested through guided sessions with municipal personnel, providing insights into how real users interact with the system. In addition, we evaluated Geminis performance in extracting relevant information from the minutes, highlighting its performance in data extraction.

Abstract

Abstract
With the surge of multimodal models and the demand for effective image Information Retrieval (IR) systems, high-quality text-to-image datasets have become paramount. However, most existing datasets are primarily in English, limiting their applicability to multilingual settings. To address this, we introduce the pt-image-ir-dataset, a manually annotated resource for text-based Image IR in European Portuguese. The dataset comprises 80 diverse queries and a curated pool of 5,201 images, each annotated for relevance by multiple human judges. The proposed dataset is a step forward in supporting the development and evaluation of image IR systems for European Portuguese, addressing a clear gap in multilingual multimodal research. To this end, we have made our dataset publicly available, alongside baseline experimental results, demonstrating its suitability on the Image IR task across different retrieval paradigms, including traditional text-based lexical IR methods, semantic dense retrieval models based on language embeddings, cutting-edge vision-language models and proprietary black-box image retrieval systems. Results demonstrate that vision-language models, particularly OpenCLIP/xlm-roberta-base-ViT-B-32, significantly outperform other approaches (MRR = 0.610).

Abstract

Abstract
Online retail is transforming the way distribution networks are managed. One prominent change is that retailers can now use their full network to fulfil orders. This process involves allocating orders to fulfilment nodes and, depending on the setting, can include other operational decisions, such as order consolidation, shipping mode selection and product substitution. This order allocation problem (OAOR) has garnered considerable attention in recent years. However, there is no comprehensive view of what has been done in the literature, nor a consistent terminology across papers, which makes it hard to position existing work and identify research gaps. To address these concerns, we conduct a systematic literature review, where we find over 60 articles contributing to the OAOR literature. From this review, we formulate the baseline problem, consider multiple extensions, and identify key problem characteristics. Additionally, we analyse and categorize the solution methods found based on the optimization mechanism, policy class, and incorporation of future information and learning. Our review points to several avenues for future research, both in problems and in solution methods.

Abstract