We introduce AI on the Pulse, a real-world-ready anomaly detection system that continuously monitors patients using a fusion of wearable sensors, ambient intelligence, and advanced AI models. Powered by UniTS, a state-of-the-art (SoTA) universal time-series model, our framework autonomously learns each patient's unique physiological and behavioral patterns, detecting subtle deviations that signal potential health risks. Unlike classification methods that require impractical, continuous labeling in real-world scenarios, our approach uses anomaly detection to provide real-time, personalized alerts for reactive home-care interventions. Our approach outperforms 12 SoTA anomaly detection methods, demonstrating robustness across both high-fidelity medical devices (ECG) and consumer wearables, with a ~22% improvement in F1 score. However, the true impact of AI on the Pulse lies in @HOME, where it has been successfully deployed for continuous, real-world patient monitoring. By operating with non-invasive, lightweight devices like smartwatches, our system proves that high-quality health monitoring is possible without clinical-grade equipment. Beyond detection, we enhance interpretability by integrating LLMs, translating anomaly scores into clinically meaningful insights for healthcare professionals.

In the past few years, knowledge graphs (KGs), as a form of structured human intelligence, have attracted considerable research attention from academia and industry. In this very active field of study, a widely explored problem is that of link prediction, the task of predicting whether two nodes should be connected, based on node attributes and local or global graph connectivity properties. The state of the art in this area is represented by techniques based on graph embeddings. However, KGs, especially those acquired using automated or partly automated techniques, are often riddled with noise, e.g., wrong relationships, which makes the problem of link deletion as important as that of link prediction. In this paper, we address three main research questions. The first is about the true effectiveness of different knowledge graph embedding models under the presence of an increasing number of wrong links. The second is to asses if methods that can predict unknown relationships effectively, work equally well in recognizing incorrect relations. The third is to verify if there are systems robust enough to maintain primacy in all experimental conditions. To answer these research questions, we performed a systematic benchmark study in which the experimental setting includes ten state-of-the-art models, three common KG datasets with different structural properties and three downstream tasks: the widely explored tasks of link prediction and triple classification, and the less popular task of link deletion. Comparative studies often yield contradictory results, where the same systems score better or worse depending on the experimental context. In our work, in order to facilitate the discovery of clear performance patterns and their interpretation, we select and/or aggregate performance data to highlight each specific comparison dimension: dataset complexity, type of task, category of models, and robustness against noise.

Knowledge is the lifeblood for a plethora of applications such as search, recommender systems and natural language understanding. Thanks to the efforts in the fields of Semantic Web and Linked Open Data a growing number of interlinked knowledge bases are supporting the development of advanced knowledge-based applications. Unfortunately, for a large number of domain-specific applications, these knowledge bases are unavailable. In this paper, we present a resource consisting of a large knowledge graph linking the Italian cultural heritage entities (defined in the ArCo ontology) with the concepts defined on well-known knowledge bases (i.e., DBpedia and the Getty GVP ontology). We describe the methodologies adopted for the semi-automatic resource creation and provide an in-depth analysis of the resulting interlinked graph.

In this paper, we present the Universal Semantic Annotator (USeA), which offers the first unified API for high-quality automatic annotations of texts in 100 languages through state-of-the-art systems for Word Sense Disambiguation, Semantic Role Labeling and Semantic Parsing. Together, such annotations can be used to provide users with rich and diverse semantic information, help second-language learners, and allow researchers to integrate explicit semantic knowledge into downstream tasks and real-world applications.

In this paper, we compare several deep and surface state-of-the-art machine learning methods for risk prediction in problems that can be modelled as a trajectory of events separated by irregular time intervals. Trajectories are the abstract representation of many real-life data, such as patient records, student e-tivities, online financial transactions, and many others. Given the continuously increasing number of machine learning methods to predict future high-risk events in these contexts, we aim to provide more insight into reproducibility and applicability of these methods when changing datasets, parameters, and evaluation measures. As an additional contribution, we release to the community the implementations of all compared methods.

Social media users readily share their preferences, life events, sentiment and opinions, and implicitly signal their thoughts, feelings, and psychological behavior. This makes social media a viable source of information to accurately and effectively mine users' interests with the hopes of enabling more effective user engagement, better quality delivery of appropriate services and higher user satisfaction. In this tutorial, we cover five important aspects related to the effective mining of user interests: (1) the foundations of social user interest modeling, such as information sources, various types of representation models and temporal features, (2) techniques that have been adopted or proposed for mining user interests, (3) different evaluation methodologies and benchmark datasets, (4) different applications that have been taking advantage of user interest mining from social media platforms, and (5) existing challenges, open research questions and exciting opportunities for further work.

This paper presents MILA, a prototype interactive Learning Analytics tool for the Moodle learning management system that has been developed to support the analysis and improvement of the teaching and learning processes in the e-learning environment of the University of Rome Unitelma Sapienza. MILA offers a variety of interactive and real-time data visualizations that provide statistics, trends, and insight information both on the Moodle-based virtual learning environment as a whole, and on each course included in it. In addition to Moodle standard logs, MILA is able to analyze tracking data generated by SCORM-compliant learning objects and to measure the duration of the related user sessions. Although MILA has been developed as a Moodle plugin, its software architecture and analysis models can be re-used and adapted to develop a learning analytics tool for any SCORM-compliant learning management system.

In this work, we address the task of extracting application-specific taxonomies from the category hierarchy of Wikipedia. Previous work on pruning the Wikipedia knowledge graph relied on silver standard taxonomies which can only be automatically extracted for a small subset of domains rooted in relatively focused nodes, placed at an intermediate level in the knowledge graphs. In this work, we propose an iterative methodology to extract an application-specific gold standard dataset from a knowledge graph and an evaluation framework to comparatively assess the quality of noisy automatically extracted taxonomies. We employ an existing state of the art algorithm in an iterative manner and we propose several sampling strategies to reduce the amount of manual work needed for evaluation. A first gold standard dataset is released to the research community for this task along with a companion evaluation framework. This dataset addresses a real-world application from the medical domain, namely the extraction of food-drug and herb-drug interactions.

We present MKGDB, a large-scale graph database created as a combination of multiple taxonomy backbones extracted from 5 existing knowledge graphs, namely: ConceptNet, DBpedia, WebIsAGraph, WordNet and the Wikipedia category hierarchy. MKGDB, thanks the versatility of the Neo4j graph database manager technology, is intended to favour and help the development of open-domain natural language processing applications relying on knowledge bases, such as information extraction, hypernymy discovery, topic clustering, and others. Our resource consists of a large hypernymy graph which counts more than 37 million nodes and more than 81 million hypernymy relations.

In this paper we present an efficient and highly accurate algorithm to prune noisy or over-ambiguous knowledge graphs given as input an extensional definition of a domain of interest, namely as a set of instances or concepts. Our method climbs the graph in a bottom-up fashion, iteratively layering the graph and pruning nodes and edges in each layer while not compromising the connectivity of the set of input nodes. Iterative layering and protection of pre-defined nodes allow to extract semantically coherent DAG structures from noisy or over-ambiguous cyclic graphs, without loss of information and without incurring in computational bottlenecks, which are the main problem of state-of-the-art methods for cleaning large, i.e., Web-scale, knowledge graphs. We apply our algorithm to the tasks of pruning automatically acquired taxonomies using benchmarking data from a SemEval evaluation exercise, as well as the extraction of a domain-adapted taxonomy from the Wikipedia category hierarchy. The results show the superiority of our approach over state-of-art algorithms in terms of both output quality and computational efficiency.

Abstract We present an approach to combining distributional semantic representations induced from text corpora with manually constructed lexical semantic networks. While both kinds of semantic resources are available with high lexical coverage, our aligned resource combines the domain specificity and availability of contextual information from distributional models with the conciseness and high quality of manually crafted lexical networks. We start with a distributional representation of induced senses of vocabulary terms, which are accompanied with rich context information given by related lexical items. We then automatically disambiguate such representations to obtain a full-fledged proto-conceptualization, i.e. a typed graph of induced word senses. In a final step, this proto-conceptualization is aligned to a lexical ontology, resulting in a hybrid aligned resource. Moreover, unmapped induced senses are associated with a semantic type in order to connect them to the core resource. Manual evaluations against ground-truth judgments for different stages of our method as well as an extrinsic evaluation on a knowledge-based Word Sense Disambiguation benchmark all indicate the high quality of the new hybrid resource. Additionally, we show the benefits of enriching top-down lexical knowledge resources with bottom-up distributional information from text for addressing high-end knowledge acquisition tasks such as cleaning hypernym graphs and learning taxonomies from scratch.

Stefano Faralli, Alexander Panchenko, Chris Biemann, Simone Paolo Ponzetto. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017.

Alexander Panchenko, Eugen Ruppert, Stefano Faralli, Simone Paolo Ponzetto, Chris Biemann. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017.

Taxonomies are an important ingredient of knowledge organization, and serve as a backbone for more sophisticated knowledge representations in intelligent systems, such as formal ontologies. However, building taxonomies manually is a costly endeavor, and hence, automatic methods for taxonomy induction are a good alternative to build large-scale taxonomies. In this paper, we propose TIEmb, an approach for automatic unsupervised class subsumption axiom extraction from knowledge bases using entity and text embeddings. We apply the approach on the WebIsA database, a database of subsumption relations extracted from the large portion of the World Wide Web, to extract class hierarchies in the Person and Place domain.

In this paper we present a minimallysupervised approach to the multi-domain acquisition of wide-coverage glossaries.We start from a small number of hypernymy relation seeds and bootstrap glossaries from the Web for dozens of domains using Probabilistic Topic Models.Our experiments show that we are able to extract high-precision glossaries comprising thousands of terms and definitions.

In 2004 we published in this journal an article describing OntoLearn, one of the first systems to automatically induce a taxonomy from documents and Web sites. Since then, OntoLearn has continued to be an active area of research in our group and has become a reference work within the community. In this paper we describe our next-generation taxonomy learning methodology, which we name OntoLearn Reloaded. Unlike many taxonomy learning approaches in the literature, our novel algorithm learns both concepts and relations entirely from scratch via the automated extraction of terms, definitions, and hypernyms. This results in a very dense, cyclic and potentially disconnected hypernym graph. The algorithm then induces a taxonomy from this graph via optimal branching and a novel weighting policy. Our experiments show that we obtain high-quality results, both when building brand-new taxonomies and when reconstructing sub-hierarchies of existing taxonomies.

In this paper we present a novel approach to learning semantic models for multiple domains, which we use to categorize Wikipedia pages and to perform domain Word Sense Disambiguation (WSD). In order to learn a semantic model for each domain we first extract relevant terms from the texts in the domain and then use these terms to initialize a random walk over the WordNet graph. Given an input text, we check the semantic models, choose the appropriate domain for that text and use the best-matching model to perform WSD. Our results show considerable improvements on text categorization and domain WSD tasks.

In this paper we present a graph-based approach aimed at learning a lexical taxonomy automatically starting from a domain corpus and the Web. Unlike many taxonomy learning approaches in the literature, our novel algorithm learns both concepts and relations entirely from scratch via the automated extraction of terms, definitions and hypernyms. This results in a very dense, cyclic and possibly disconnected hypernym graph. The algorithm then induces a taxonomy from the graph. Our experiments show that we obtain high-quality results, both when building brand-new taxonomies and when reconstructing WordNet sub-hierarchies. 1

Current research in interaction aims at defining new types of multimedia and multimodal experience, at enriching everyday objects and environments with the ability to capture user actions and intentions, and at integrating real and virtual sources of information, typically exploiting the visual channel. These forms of interaction usually require dedicated architectures, often relying on different component models, and with rigid types of configuration. We present an approach to the integration of real and virtual world sensors and effectors, and of traditional multimedia environments within a single component-based architecture. Environments in this architecture are defined as networks of plugins, each equipped with computational, presentation and communication capabilities. Examples of integrated environments produceable with this architecture are given.

We present HYPERSCORE, a system for interactive execution of musical performances coupled with the generation system CLIPSCORE, in which a performer can virtually manipulate execution parameters through gestural interaction in real time. HYPERSCORE allows users to exploit their perceptive capabilities in terms of space and time in order to control and manipulate, via a multimodal interaction, the main component of music, namely time.