Papers by Prof. Guido Vetere

Frontiers in artificial intelligence and applications, Jun 22, 2023
Despite recent advances in automation, customer support still requires a substantial amount of hu... more Despite recent advances in automation, customer support still requires a substantial amount of human intervention through voice channels. With the aim of improving the work of human assistants, we developed a collaborative bot (cobot) to help them in the process of handling customer voice interactions. The cobot is a reasoning agent that starts from loading background customer data into a dynamic knowledge graph. Then it captures the audio stream of the conversation, converts it to text in real time, analyzes the blocks of conversation with neural technologies and "thinks" about the results. Assistants can also supply data to the cobot, based on the information they gather from the ongoing conversation. The reasoning agent provides information and action suggestions to the human assistant by applying heuristics on data collected from both automatic and human sources, based on a task and domain-specific conceptual models (ontologies). While designing a prototypical solution for utility services in Italy, we are faced with many problems, including spontaneous speech understanding, factual and linguistic knowledge representation, and efficient heuristic reasoning. We adopted a standards-based approach and experimented with open source reasoners and publicly available language models. The paper presents preliminary findings and outlines the system design, with focus on the interplay of neural language processing and logic reasoning.
Knowledge Graph Foundations
Enterprise Knowledge Graph: Looking into the Future
Congratulations! We have covered architecture, technical details, and success stories of the know... more Congratulations! We have covered architecture, technical details, and success stories of the knowledge graph for Large Organizations together, in the eight chapters that we have just walked over.

Formal Ontology in a Relativistic Setting
Ontologies are supposed to address the problem of making information systems’ conceptual models s... more Ontologies are supposed to address the problem of making information systems’ conceptual models shareable and understandable. Most often, however, ontologies are nothing but structured lexical resources, which bring with them the classic problem behind natural language meanings: how to make sure that names and predicates are consistently interpreted all through the information sphere? Here is where formal ontology comes to play. In fact, the ‘ontological level’ [1, 3] is where, thanks to formal constraints (meaning axioms), unintended models (spurious interpretations) should be cut off. Yet, interpreting well-founded, highly formalized ontologies is far from trivial, and does not come for free. What makes ontology so difficult in practice? How to make concepts understandable and alleviate the burden of mapping strict ontological specifications with business data? This short paper will provide a brief overview on common issues when working with formal ontology and how to address them...
Formal Ontology to the Proof of Facts

Peer to Peer (P2P) networks are networks where each system (peer) can act both as data provider a... more Peer to Peer (P2P) networks are networks where each system (peer) can act both as data provider and consumer, without hierarchies or (crucial) dependencies on centralized components. P2P information integration takes place when, within some peer with respect to other peers, a dependency between provided and consumed information is established. Peers can either manage their own data schemas or adopt a shared ontology. In any case, they answer queries posed in a given terminology by accessing local data sources and/or by querying other peers basing on a suitable set of mappings. The striking di erence between P2P systems and centralized ones is the distribution of the integration logic [5]. While traditional information integration architectures are based on speci c components (e.g. service bus), P2P integration is, potentially, everywhere. This poses the problem of having semantic commitments (i.e. speci c interpretations of schemas over data items) distributed all around the network...

La vita sociale e sempre piu fortemente connessa alle piattaforme digitali: relazioni personali, ... more La vita sociale e sempre piu fortemente connessa alle piattaforme digitali: relazioni personali, commerci, partecipazione politica, servizi pubblici e privati, si sviluppano nelle modalita e alle condizioni che tali sistemi predispongono. Un piccolo numero di tali piattaforme, gestite per lo piu da societa private statunitensi, hanno conquistato posizioni dominanti non solo in importanti settori economici, ma anche nella sfera dell’influenza politica e culturale, ed esercitano oggi poteri paragonabili a quelli degli Stati nazionali. Si invoca da piu parti una governance che tuttavia, per il carattere globale del fenomeno e per la massa critica raggiunta da tali concentrazioni, appare problematica. Una prospettiva spesso evocata e quella del ripristino dell’equilibrio del Web delle origini: un sistema decentralizzato e paritario. Sulla via di questo ritorno alle condizioni iniziali si presentano tuttavia alcuni problemi tecnici e sociali per superare i quali sara necessario affrontar...
Enterprise Knowledge Graph: An Introduction
Exploiting Linked Data and Knowledge Graphs in Large Organisations, 2017
Compared to other knowledge-oriented information systems, the distinctive features of Knowledge G... more Compared to other knowledge-oriented information systems, the distinctive features of Knowledge Graphs lie in their special combination of knowledge representation structures, information management processes, and search algorithms.
In Natural Language Processing, more complex business use cases and shorter delivery times drive ... more In Natural Language Processing, more complex business use cases and shorter delivery times drive a growing need of smoother, more exible and faster implementations. This trend also requires integrating and orchestrating di�erent functionalities delivered by services belong- ing to di�erent technological platforms. All these needs imply raising the level of abstraction for NLP components development. In this paper we present a Model Driven Architecture approach suitable to develop an open and interoperable UIMA-based NLP stack. By decoupling UIMA NLP models from other solution speci�c platforms and services, we ob- tain major architectural improvements.
This paper reports on research activities on automatic methods for the enrichment of the Senso Co... more This paper reports on research activities on automatic methods for the enrichment of the Senso Comune platform. At this stage of development, we will report on two tasks, namely word sense alignment with MultiWordNet and automatic acquisition of Verb Shallow Frames from sense annotated data in the MultiSemCor corpus. The results obtained are satisfying. We achieved a final F-measure of 0.64 for noun sense alignment and a F-measure of 0.47 for verb sense alignment, and an accuracy of 68% on the acquisition of Verb Shallow Frames.
This work describes the evaluations of two approaches, Lexical Matching and Sense Similarity, for... more This work describes the evaluations of two approaches, Lexical Matching and Sense Similarity, for word sense alignment between MultiWordNet and a lexicographic dictionary, Senso Comune De Mauro, when having few sense descriptions (MultiWordNet) and no structure over senses (Senso Comune De Mauro). The results obtained from the merging of the two approaches are satisfying, with F1 values of 0.47 for verbs and 0.64 for nouns. Lexical Match P R F1 Acc.
Sistemi Evoluti per Basi di Dati, 2006
Services represent over 70 percent of the economy in western countries and the segment is growing... more Services represent over 70 percent of the economy in western countries and the segment is growing rapidly 44

Workpad peer-to-peer information integration system for crisis management
Sistemi Evoluti per Basi di Dati, 2008
The invention provides a novel key-board switching unit used, for example, in pocketable electron... more The invention provides a novel key-board switching unit used, for example, in pocketable electronic calculators for producing binary-coded signals corresponding to contacting of movable contact points on the bottom surface of a keyboard covering pad and fixed contact points on the printed circuit board on which the covering pad is mounted when pushed with a finger tip or a pushing means. The printed circuit board in the inventive switching unit has a so fine and complicated circuit pattern that, in the prior art, one or more of jumping circuits crossing over a printed base pattern are indispensable resulting in much increased production costs while, in the inventive switching unit, the circuit pattern on the circuit board per se may be incomplete by the lack of such jumping circuits and, instead, the covering pad is provided with conductive connections corresponding to the lacking jumping circuits on the circuit board to form necessary jumping circuits when the covering pad is mounted on the circuit board.

Lecture Notes in Computer Science, 2004
Data Grids allow for seeing heterogeneous, distributed, and dynamic informational resources as if... more Data Grids allow for seeing heterogeneous, distributed, and dynamic informational resources as if they were a uniform, stable, secure, and reliable database. According to this view, current proposals for data integration on Grids are based on the notion of global schema built over a collection of autonomous information sources. On the other hand, in dynamic and distributed environments, such a hierarchical and centralized architecture is not well suited for effective information integration. Peer-to-peer data integration aims at overcoming these drawbacks by modeling autonomous information systems as peers, and establishing mappings among peers without resorting to any hierarchical structure. In this paper, we present Hyper, a joint research initiative of Università di Roma "La Sapienza" and IBM Italia, which aims at developing principles and techniques for peer-to-peer data integration on a Grid infrastructure. The main contributions presented are a semantic characterization of P2P data integration, the deployment of our P2P framework on a Grid architecture, and the design of a query answering algorithm that is coherent both with the semantics and with the Grid infrastructure.
p-arch.it
La mancanza di un lessico computazionale aperto per la lingua italiana limita l'accesso alle... more La mancanza di un lessico computazionale aperto per la lingua italiana limita l'accesso alle risorse informative in rete nel nostro Paese. Questo riguarda anche il patrimonio informativo della Pubblica Amministrazione, la cui accessibilitae da molti anni ...
From Data to Knowledge, the Role of Formal Ontology
Proceeding of the 2009 conference on Formal …, 2009
The increasing availability of large amounts of data and the growing capability of accessing and ... more The increasing availability of large amounts of data and the growing capability of accessing and processing them, gives us today unprecedented opportunities to advance in many fields, including science, commerce, social relations, government, and business, ...
ceur-ws.org, 2005
Abstract. Peer-to-Peer computing (P2P) is a model in which each system acts potentially as both c... more Abstract. Peer-to-Peer computing (P2P) is a model in which each system acts potentially as both client and server, and systems link the one another without resorting on centralized services. Thanks to its generality, flexibility, and scalability, P2P is one of the prominent ...
OntoLex 2008 Programme, 2008
Following a fashionable recent trend in the scientific community, computational lexicons are ofte... more Following a fashionable recent trend in the scientific community, computational lexicons are often said to incorporate or even correspond to linguistic ontologies, whose purpose is to describe semantic constructs of language (bound to grammatical units). ...
IBM Systems Journal, 2005
Although service-oriented architectures go a long way toward providing interoperability in distri... more Although service-oriented architectures go a long way toward providing interoperability in distributed, heterogeneous environments, managing semantic differences in such environments remains a challenge. We give an overview of the issue of semantic interoperability (integration), provide a semantic characterization of services, and discuss the role of ontologies. Then we analyze four basic models of semantic interoperability that differ in respect to their mapping between service descriptions and ontologies and in respect to where the evaluation of the integration logic is performed. We also provide some guidelines for selecting one of the possible interoperability models.

Comune is an open-knowledge base for the Italian language, available through a Web-based collabor... more Comune is an open-knowledge base for the Italian language, available through a Web-based collaborative platform, whose construction is in progress. The resource integrates dictionary data coming from both users and legacy resources with an ontological backbone, which provides foundations for a formal characterization of lexical semantic structures (frames). A nucleus of basic Italian lemmas, which have been semantically analyzed and classified, is available for both online access and downloading. A restricted community of contributors is currently working on increasing the lexical coverage of the resource. Research is underway to extend the knowledge base model to encompass verbal frames. RÉSUMÉ. Senso Comune est une base de connaissances ouverte de la langue italienne, disponible à travers une plateforme collaborative sur le Web, dont la construction est en cours. Cette ressource intègre les données lexicographiques provenant à la fois d'utilisateurs et de dictionnaires existants avec une ossature ontologique qui fournit les bases pour une caractérisation formelle de structures sémantiques lexicales (cadres). Un noyau de lemmes italiens de base, qui ont été analysés et classés sémantiquement, est disponible à la fois pour l'accès en ligne et le téléchargement. Une petite communauté de contributeurs travaille actuellement sur l'augmentation de la couverture lexicale de la ressource. Les recherches en cours visent à étendre le modèle de base de connaissances pour inclure les cadres verbaux.
Uploads
Papers by Prof. Guido Vetere