Systematic reviews are vital for evidence-based decision-making but remain resource-intensive due to the volume of literature requiring expert screening.Technology-Assisted Review (TAR) systems offer a solution by ranking documents for review, yet questions remain about how best to allocate limited human effort across multiple review topics.In this paper, we explore the problem of effort distribution by comparing alternative screening policies under fixed effort constraints.Using real-world data from the CLEF eHealth 2017-2019 TAR tasks, we evaluate both baseline and adaptive policies that account for topic size, screening depth, and residual uncertainty.We introduce effort-aware evaluation metrics to measure trade-offs between review effectiveness and resource use.Our results show that simple, topic-sensitive policies can significantly improve the yield of relevant documents discovered, offering practical insights for scalable and equitable systematic review workflows.

The paper reports on the first results of the design and implementation of a new digital tool for romance philology: the digital Onomastic Repertoire for the medieval French romance (12th-15th centuries). This tool, projected with a modular and integrable architecture, was implemented from a selection of romances, the corpus of the Medieval French Roman d’Alexandre. After introducing the peculiarities of the onomastic system in the Middle Ages (and, more generally, the peculiarities of medieval literary texts), the paper describes 1) the methodological challenges faced in the preparatory work, illustrates and comments on the first results achieved and 2) the design and implementation of the first integrated system for the interactive creation of the Onomastic Repertoire of the romaN d’AlexandRE (ORNARE), and 3) the current research output in terms of both a digital edition and the digital onomastic index of the corpus.

The process of standardization plays an important role in the management of terminological resources. In this context, we present the work of re-modeling an existing multilingual terminological database for the medical domain, named TriMED. This resource was conceived in order to tackle some problems related to the complexity of medical terminology and to respond to different users’ needs. We provide a methodology that should be followed in order to make a termbase compliant to the three most recent ISO/TC 37 standards. In particular, we focus on the definition of i) the structural meta-model of the resource, ii) the data categories provided, and iii) the TBX format for its implementation. In addition to the formal standardization of the resource, we describe the realization of a new data category repository for the management of the TriMED terminological data and a Web application that can be used to access the multilingual terminological records.

The Precision Medicine (PM) track at the Text REtrieval Conference (TREC) focuses on providing useful precision medicine-related information to clinicians treating cancer patients. The PM track gives the unique opportunity to evaluate medical IR systems using the same set of topics on two different collections: scientific literature and clinical trials. In the paper, we take advantage of this opportunity and we propose and evaluate state-of-the-art query expansion and reduction techniques to identify whether a particular approach can be helpful in both scientific literature and clinical trial retrieval. We present those approaches that are consistently effective in both TREC editions and we compare the results obtained with the best performing runs submitted to TREC PM 2017 and 2018.

In-region location verification (IRLV) in wireless networks is the problem of deciding if user equipment (UE) is transmitting from inside or outside a specific physical region (e.g., a safe room). The decision process exploits the features of the channel between the UE and a set of network access points (APs). We propose a solution based on machine learning (ML) implemented by a neural network (NN) trained with the channel features (in particular, noisy attenuation values) collected by the APs for various positions both inside and outside the specific region. The output is a decision on the UE position (inside or outside the region). By seeing IRLV as an hypothesis testing problem, we address the optimal positioning of the APs for minimizing either the area under the curve (AUC) of the receiver operating characteristic (ROC) or the cross entropy (CE) between the NN output and ground truth (available during the training). In order to solve the minimization problem we propose a two-stage particle swarm optimization (PSO) algorithm. We show that for a long training and a NN with enough neurons the proposed solution achieves the performance of the Neyman-Pearson (N-P) lemma.

In-region location verification (IRLV) aims at verifying whether a user is inside a region of interest (ROI). In wireless networks, IRLV can exploit the features of the channel between the user and a set of trusted access points. In practice, the channel feature statistics is not available and we resort to machine learning (ML) solutions for IRLV. We first show that solutions based on either neural networks (NNs) or support vector machines (SVMs) with typical loss functions are Neyman-Pearson (N-P)-optimal at learning convergence for sufficiently complex learning machines and large training datasets. For a finite training, ML solutions are more accurate than the N-P test based on estimated channel statistics. Then, as estimating channel features outside the ROI may be difficult, we consider one-class classifiers, namely auto-encoder NNs and one-class SVMs which, however, are not equivalent to the generalized likelihood ratio test (GLRT), typically replacing the N-P test in the one-class problem. Numerical examples support the results in realistic wireless networks, with channel models including path-loss, shadowing, and fading.

Nowadays, most mobile devices are equipped with multiple wireless interfaces, causing an emerging research interest in device to device (D2D) communication: the idea behind the D2D paradigm is to exploit the proper interface to directly communicate with another user, without traversing any network infrastructure. A first issue related to this paradigm is the need for a coordinator, called controller, able to decide when activating a D2D connection is appropriate and to manage such connection. In this view, the paradigm of Software Defined Networking (SDN) can be exploited both to handle the data flows among the devices and to interact directly with every device. This work is focused on a scenario where a device is selected by the SDN controller, in order to become the master node of a WiFi-Direct network. The remaining nodes, called clients, can exchange data with other nodes through the master. The objective is to infer, through different Machine Learning approaches, the number of nodes actively involved in receiving data, exploiting only the information available at the client side and without modifying any standard communication protocol. The information about the number of client nodes is crucial when, e.g., a user desires a precise prediction of the transmission estimated time of arrival (ETA) while downloading a file.

In this demo, we present a web application which allows users to interact with two retrieval models, namely the Binary Independence Model (BIM) and the BM25 model, on a standard TREC collection. The goal of this demo is to give students deeper insight into the consequences of modeling assumptions (BIM vs. BM25) and the consequences of tuning parameter values by means of a two-dimensional representation of probabilities. The application was developed in R, and it is accessible at the following link: http://gmdn.shinyapps.io/shinyRF04.

Digital Geolinguistic systems encourage collaboration between linguists, historians, archaeologists, ethnographers, as they explore the relationship between language and cultural adaptation and change. In this demo, we propose a Linked Open Data approach for increasing the level of interoperability of geolinguistic applications and the reuse of the data. We present a case study of a geolinguistic project named Atlante Sintattico d'Italia, Syntactic Atlas of Italy (ASIt).

Naive-Bayes (NB) classifiers are simple probabilistic classifiers still widely used in supervised learning due to their tradeoff between efficient model training and good empirical results. One of the drawbacks of these classifiers is that in situations of data sparsity (i.e. when the size of training set is small) the maximum likelihood estimation of the probability of unseen features in these situations is equal to zero causing arithmetic anomalies. To prevent this undesirable behavior, a number of smoothing techniques have been proposed. Among these, the Bayesian approach incorporates smoothing in terms of prior knowledge about the parameters of the model usually called hyper-parameters. Our research question is: can a visualization tool help researchers to quickly assess the goodness of the performance of NB classifiers by setting optimal smoothing parameters?