Ricerc@Sapienza

Most programming languages only support tests that refer exclusively to the current state. This applies even to high-level programming languages based on the situation calculus such as Golog. The result is that additional variables/fluents/data structures must be introduced to track conditions that the pro- gram uses in tests to make decisions.

Recent research indicates that taking advantage of complex syntactic features leads to favorable results in Semantic Role Labeling. Nonetheless, an analysis of the latest state-of-the-art multilingual systems reveals the difficulty of bridging the wide gap in performance between high-resource (e.g., English) and low-resource (e.g., German) settings. To overcome this issue, we propose a fully language-agnostic model that does away with morphological and syntactic features to achieve robustness across languages.

Semantic Role Labeling (SRL) is deeply dependent on complex linguistic resources and sophisticated neural models, which makes the task difficult to approach for non-experts. To address this issue we present a new platform named Intelligible Verbs and Roles (InVeRo). This platform provides access to a new verb resource, VerbAtlas, and a state-of-the-art pre-trained implementation of a neural, span-based architecture for SRL.

In Silico Clinical Trials (ISCT), i.e., clinical experimental campaigns carried out by means of computer simulations, hold the promise to decrease time and cost for the safety and efficacy assessment of pharmacological treatments, reduce the need for animal and human testing, and enable precision medicine.

This special issue of the International Journal of Approximate Reasoning (IJAR) focuses on recent advances in soft methods in probability and statistics.The special issue is a follow-up of the 8th International Conference on Soft Methods in Probability and Statistics (SMPS2016),which took place in Rome (Italy) in September 2016 (http://www.sbai.uniroma1.it/smps2016/index.php).

The detection of patterns in multivariate time series is a relevant task, especially for large datasets. In this paper, four clustering models for multivariate time series are proposed, with the following characteristics. First, the Partitioning Around Medoids (PAM) framework is considered. Among the different approaches to the clustering of multivariate time series, the observation-based is adopted. To cope with the complexity of the features of each multivariate time series and the associated assignment uncertainty a fuzzy clustering approach is adopted.

Obiettivo dell’articolo è capire come la crisi COVID-19 in corso sta influenzando i processi politici e di regolazione in Italia. A questo fine sono messe a fuoco alcune caratteristiche e conseguenze politiche dell’iniziativa governativa finalizzata a supportare, attraverso la tecnologia di intelligenza artificiale (AI) “Immuni” per il contact tracing della popolazione, la transizione a una fase di maggiore mobilità dopo quella di lockdown.

The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is α∼0.14, far from the theoretical bound for symmetric networks, i.e. α=1.

Nowadays, the development of data management technologies has deeply contributed to make
immediate and effective the activity of gathering and processing large amounts of data with
reference to specific process or performance indicators. The Big Data phenomenon along with
Artificial Intelligence (AI) techniques represent a new era in information exploration and
utilization, by offering new perspectives in the decision-making processes, especially in complex
and fragmented situation. In this way, the emerging knowledge derived pushes toward new models