2021
Other
Open Access
Enhancing the computational representation of narrative and its extraction from text
Metilli DNarratives are a fundamental part of human life. Every human being encounters countless stories during their life, and these stories contribute to form a common understanding of reality. This is reflected in the current digital landscape, and especially on the Web, where narratives are
published and shared everyday.
However, the current digital representation of narratives is limited by the fact that each narrative is generally expressed as natural language text or other media, in an unstructured way that is neither standardized nor machine-readable. These limitations hinder the manageability of narratives by automated systems.
One way to solve this problem would be to create an ontology of narrative, i.e., a formal model of what a narrative is, then develop semi-automated methods to extract narratives from natural language text, and use the extracted data to populate the ontology. However, the feasibility of this approach remains an open question.
This thesis attempts to investigate this research question, starting from the state of the art in the fields of Computational Narratology, Semantic Web, and Natural Language Processing. Based on this analysis, we have identified a set of requirements, and we have developed a methodology for our research work.
Then, we have developed an informal conceptualization of narrative, and we have expressed it in a formal way using First-Order Logic. The result of this work is the Narrative Ontology (NOnt), a formal model of narrative that also includes a representation of its textual structure and textual semantics. To ensure interoperability, the ontology is based on the CIDOC CRM and FRBRoo standards, and it has been expressed using the OWL and SWRL languages of the Semantic Web.
Based on the ontology, we have developed NarraNext, a semi-automatic tool that is able to extract the main elements of narrative from natural language text. The tool allows the user to create a complete narrative based on a text, using the extracted knowledge to populate the ontology. NarraNext is based on recent advancements in the Natural Language Processing field, including deep neural networks, and is integrated with the Wikidata knowledge base.
The validation of our work is being carried out in three different scenarios: (i) a case study on biographies of historical figures found in Wikipedia; (ii) the Mingei project, which applies NOnt to the representation and preservation of Heritage Crafts; (iii) the Hypermedia Dante Network project, where NOnt has been integrated with a citation ontology to represent the content of Dante's Comedy.
All three applications have served to validate the representational adequacy of NOnt and the satisfaction of the requirements we defined. The case study on biographies has also evaluated the effectiveness of the NarraNext tool.Project(s): Mingei 
See at:
etd.adm.unipi.it
| CNR IRIS
| ISTI Repository
| CNR IRIS
2016
Conference article
Restricted
Usability evaluation of the digital library DanteSources
Bartalesi V, Meghini C, Metilli D, Andriani PIn this paper we present DanteSources, a Digital Library of Dante Alighieri's primary sources, i.e. the works of other authors that Dante cites in his texts. Currently, this information is scattered in many books, making it difficult for the scholars to retrieve it and also to produce a systematical overview of the cultural background of Dante. In order to overcome this problem, an ontology expressed in RDF/S was developed to represent this knowledge. Once the ontology had been defined, we populated it with the data included in authoritative commentaries to Dante's works. We stored the resulting RDF graph into a Virtuoso triple store. Finally, on top of this graph, we developed DanteSources, which allows users to extract and display the knowledge stored in the knowledge base in the form of charts and tables. In this paper we present the results of a survey to collect suggestions and comments from end-users on their interactions with DanteSources in order to evaluate its usability.DOI: 10.1007/978-3-319-39513-5_18Metrics:
See at:
doi.org
| CNR IRIS
| CNR IRIS
| link.springer.com
2016
Conference article
Restricted
Steps towards accessing digital libraries using narratives
Meghini C, Bartalesi V, Metilli DOne of the main problems of the current Digital Libraries (DLs) is the limitation of the informative services offered to the users. Indeed, DLs provide simple search functionalities which return a list of the information objects contained in them. No semantic relation among the returned objects is usually reported which can help the user in obtaining a more complete knowledge on the subject of the search. The introduction of the Semantic Web has the potential of improving the search functionalities of DLs. Many cultural institutions have represented their metadata into formal descriptions encoded by means of formal languages such as RDF and OWL. In this context, the aim of our research is to introduce the narrative as a new search functionality which does not only return a list of objects but presents a narrative, composed of events that are linked to the objects of the library and endowed with a set of semantic relations connecting these events into a meaningful semantic network. The paper presents the first theoretical achievements on a model for representing narratives.Source: CEUR WORKSHOP PROCEEDINGS, pp. 10-17. Genova, Italy, 28 November 2016
Project(s): PARTHENOS 
See at:
ceur-ws.org
| CNR IRIS
| CNR IRIS
2017
Contribution to book
Restricted
Using Formal Narratives in Digital Libraries
Meghini C, Bartalesi V, Metilli DCurrently, Digital Libraries (DLs) provide simple search functionalities to respond to the user's queries, which return a ranked list of the resources included in the DLs. No semantic relation among the returned objects is usually reported that could help the user to obtain a more complete knowledge on the subject of the search. The introduction of the Semantic Web and in particular of the Linked Open Data has the potential of improving the search functionalities of DLs. In this context, the long-term aim of our study has been to introduce the narrative as new first-class search functionality of DLs. We intend narratives as semantic networks of events that are linked to the objects of the DLs and are endowed with a set of semantic relations that connect an event to another. In this paper, we report an overview of the main ontologies for representing events and of the tools developed in the Semantic Web field to visualize events and narratives. This overview is needed for achieving the first goal of our research, that is the development of an ontology for representing narratives and, on the top of this ontology, a tool to construct and visualize narratives using the digital objects included in DLs.Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE (PRINT), pp. 83-94
DOI: 10.1007/978-3-319-68130-6_7Project(s): PARTHENOS
Metrics:
See at:
doi.org
| CNR IRIS
| CNR IRIS
| link.springer.com
2018
Journal article
Open Access
A web application for exploring primary sources: the DanteSources case study
Bartalesi V, Meghini C, Metilli D, Tavoni M, Andriani PWe present the methodological and technical process we adopted to develop DanteSources, a Web application that allows free access to the knowledge about Dante Alighieri's primary sources, i.e. the works of other authors that Dante cites in his texts. Up to now, this knowledge has been collected in many paper books, making it difficult for the scholars to retrieve it and to produce a complete overview of these data. Using Semantic Web technologies, we developed an ontology expressed in the Resource Description Framework Schema vocabulary providing the terms to represent this knowledge in a machine-readable form. A semi-automatic tool helps the scholars to populate the ontology with the data included in authoritative paper commentaries to Dante's works. Then, the tool automatically saves the resulting Resource Description Framework graph in a triple store. On top of this graph, we developed DanteSources, a Web application that allows users to extract and display the information stored in the knowledge base in the form of charts and tables. Finally, we report the results of a survey to collect suggestions from end-users on their interactions with DanteSources. The methodology and the tools we developed are easily reusable, e.g. to represent the knowledge about primary sources of other authors of the Italian and the international literature.Source: DIGITAL SCHOLARSHIP IN THE HUMANITIES, vol. 33 (issue 4), pp. 705-723
DOI: 10.1093/llc/fqy002Metrics:
See at:
academic.oup.com
| Digital Scholarship in the Humanities
| CNR IRIS
| ISTI Repository
| CNR IRIS
| CNR IRIS
2019
Conference article
Open Access
Constructing narratives using NBVT: a case study
Bartalesi V, Metilli D, Meghini CNarratives are a fundamental part of human life, starting from the epic poems of the ancient past to modern films. Since the 1970s, much research has been carried out to study the computational representation of narratives. Up to now, there is no standard definition of narrative. In our research, we intend narratives as networks of events defined by a narrator, endowed with participating entities (e.g. persons, location, time) and semantic relations. In this paper, we introduce the Narrative Building and Visualising Tool (NBVT), a semi- automatic software based on a formal ontology for narratives we developed. The tool allows users to construct and visualise narratives using Wikidata as reference knowledge base and Europeana for enriching the narrative with digital objects. As case study, we present the narrative of the life of the Austrian painter Gustav Klimt created using NBVT. Since Wikidata is not event-based, our efforts focus on the automatic extraction from Wikidata of the implicit events that compose the narrative. Furthermore, we developed a dedicated functionality in NBVT that finds the Europeana digital objects related to a particular event. This functionality matches the metadata of Europeana digital objects with the event and the participating entities using a similarity algorithm.
See at:
aiucd2019.uniud.it
| CNR IRIS
| ISTI Repository
| CNR IRIS
2016
Journal article
Restricted
DanteSources: una biblioteca digitale delle fonti dantesche
Bartalesi V, Andriani P, Metilli D, Meghini C, Tavoni MUn tipo importante di conoscenza studiata in campo umanistico è rappresentato dalle fonti primarie di testi letterari, ovvero le opere di altri autori a cui uno scrittore fa riferimento nei propri testi. Solitamente questa conoscenza è riportata nei commentari ai testi letterari, scritti in linguaggio naturale, di cui i lettori si servono per studiare in profondità i diversi aspetti di queste opere. Sfortunatamente questa conoscenza non è disponibile in un formato digitale leggibile da un computer, perciò non è possibile per gli studiosi ottenere inferenze automatiche che, seppur semplici, potrebbero essere utili per i loro studi (ad esempio la distribuzione delle fonti primarie e degli autori citati in una determinata opera).
Il nostro studio si colloca nell'ambito del progetto di ricerca nazionale (PRIN 2013-2016) "Per una enciclopedia dantesca digitale . Lo scopo della nostra ricerca è quello di costruire una biblioteca digitale dotata di servizi a supporto degli studiosi per creare, arricchire e consultare una enciclopedia digitale delle opere di Dante Alighieri. In particolare, il nostro studio mira a supportare gli studiosi nell'espressione formale e nell'accesso alla conoscenza riguardante le fonti primarie citate nelle opere di Dante Alighieri, e più in generale nei testi letterari. In questo articolo descriviamo la metodologia e il processo di sviluppo che abbiamo seguito per creare DanteSources, una biblioteca digitale che fornisce libero accesso alle informazioni riguardanti le fonti primarie di Dante Alighieri. Illustriamo qui l'intero processo, dalla creazione dell'ontologia per rappresentare la conoscenza riguardante le fonti primarie fino allo sviluppo della biblioteca.
La metodologia e gli strumenti che abbiamo sviluppato all'interno del progetto sono facilmente riutilizzabili per rappresentare la conoscenza riguardante le fonti primarie di altri autori della letteratura italiana e internazionale.Source: LE FORME E LA STORIA, vol. IX
DOI: 10.1400/256610Metrics:
See at:
CNR IRIS
| CNR IRIS
| www.torrossa.com
2017
Conference article
Restricted
L'esplorazione delle fonti dantesche attraverso la biblioteca digitale DanteSources
Tavoni M, Andriani P, Meghini C, Bartalesi V, Metilli DNegli ultimi anni abbiamo potuto assistere a un intensificarsi dei rapporti di collaborazione fra l'informatica e le scienze umane. L'area di ricerca delle Digital Humanities (o Informatica Umanistica) ha visto infatti un moltiplicarsi di progetti di digitalizzazione e un incremento e raffinamento degli strumenti informatici per la rappresentazione e il trattamento di dati provenienti dall'ambito umanistico. Un ambito di ricerca che sta conoscendo un notevole sviluppo è quello del Semantic Web, che sperimenta nuovi linguaggi e modelli di dati per la rappresentazione dei livelli semantici nelle risorse informative,
consentendone l'elaborazione automatica. È in questo campo di indagine che si inserisce la biblioteca digitale DanteSources. 1 DanteSources nasce nell'ambito del progetto di ricerca nazionale "Per una enciclopedia dantesca digitale" (PRIN 2013-2016), coordinato da Marco Santagata, nato con lo scopo di costruire una biblioteca digitale in grado di fornire servizi di supporto agli studiosi per creare, arricchire e consultare una enciclopedia digitale delle opere di Dante Alighieri. In particolare, DanteSources si concentra sulla rappresentazione della conoscenza riguardante le fonti citate nelle opere di Dante Alighieri, ovvero le opere di altri autori a cui Dante fa riferimento nei propri testi. Solitamente questa conoscenza è riportata in testi a stampa e non è disponibile in formato digitale, perciò non è possibile per gli studiosi ottenere inferenze automatiche che, seppur semplici, potrebbero essere utili per i loro studi: ad esempio la distribuzione delle fonti e degli autori citati in una determinata opera. DanteSources rappresenta queste informazioni tramite le metodologie e i linguaggi del Semantic Web, e le rende disponibili in un formato facilmente interpretabile da strumenti informatici, in modo da consentire un salto di qualità nell'analisi delle fonti dantesche. In questo articolo descriviamo il processo di sviluppo seguito per la creazione della biblioteca digitale, dalla creazione dell'ontologia per rappresentare la conoscenza riguardante le fonti fino allo sviluppo della biblioteca digitale. La metodologia e gli strumenti che abbiamo sviluppato all'interno del progetto sono facilmente riutilizzabili per rappresentare la conoscenza riguardante le fonti di altri autori della letteratura italiana e internazionale.
See at:
CNR IRIS
| CNR IRIS
2019
Journal article
Open Access
What is needed to digitise knowledge on Heritage Crafts?
Zabulis X, Meghini C, Partarakis N, Kaplanidi D, Doulgeraki P, Karuzaki E, Stefanidi E, Evdemon T, Metilli D, Bartalesi V, Fasoula M, Tasiopoulou E, Beisswenger CHeritage Crafts (HCs) involve tangible craft artefacts, materials, and tools and encompass traditional craftsmanship as a form of Intangible Cultural Heritage. Intangible HC dimensions include dexterity, know-how, and skilled use of tools, as well as identity and traditions of the communities in which craftsmanship is, or was, practiced. Despite their cultural significance, efforts towards HC digital representation and presentation are scattered. In the Mingei EU Innovation Action, an approach is developed towards systematising the representation of Heritage Crafts as Cultural Heritage for their preservation. The representation is expected to capture the wide spectrum of knowledge topics that HCs cover, from objects and their making, to hand gestures and tool uses that define craft motor skills, to the societal value, economic impact, and historical significance. In this article, we focus on
the approach towards the creation of a knowledge and its representation. Examples and experiments are presented for two craft instances that are studied in this action.Source: MEMORIAMEDIA, vol. 1 (issue 4), pp. 1-25
Project(s): Mingei 
See at:
CNR IRIS
| memoriamedia.net
| ISTI Repository
| CNR IRIS
2015
Software
Metadata Only Access
DanteSources
Bartalesi Lenzi V, Meghini C, Andriani P, Metilli DDanteSources is a tool that allows you to retrieve information about Dante's primary sources. DanteSources allows you to visualize through tables and charts the list and the distribution of primary sources, authors and thematic areas cited by Dante in his works.
See at:
CNR IRIS
| perunaenciclopediadantescadigitale.eu
2017
Software
Metadata Only Access
Narrative building and visualising tool
Metilli D, Bartalesi Lenzi V, Meghini CThe Narrative Building and Visualising Tool (NBVT) is a semi-automatic tool to construct and visualise narratives, intended as semantic networks of events related each other through semantic relations. This tool obeys an ontology for narratives. NBVT uses Wikidata/Wikimedia Commons as external knowledge base of images and entities. The user of NBVT can select instances of the narratives ontologies among automatically proposed Wikidata entities, otherwise new entities can be created. NBVT assigns URIs to the selected instances and facilitates the construction of events based on these instances, and their linking to form narratives. The knowledge collected by the tool is exported as Linked Data.Project(s): PARTHENOS 
See at:
dlnarratives.eu
| CNR IRIS
2017
Journal article
Open Access
A conceptualisation of narratives and its expression in the CRM
Bartalesi Lenzi V, Meghini C, Metilli DCurrent Digital Libraries (DLs) are mostly built around large collections of scarcely related objects. We aim at enriching the information space of DLs by introducing narratives, consisting of two main components: networks of events related to one another and to the DL resources through semantic links, and narrations of those events in texts. In order to introduce narratives in DLs, we developed a conceptualisation based on narratology and we expressed it using the CIDOC CRM and CRMinf as reference ontologies. We used this expression to validate our conceptualisation, creating a narrative of the biography of Dante Alighieri as a realistic case study. To support this experiment, we developed a semi-automated tool that collects basic knowledge about objects and events from Wikidata. The developed ontology is general enough to be not limited to create biographies but other types of narratives as well.Source: INTERNATIONAL JOURNAL OF METADATA, SEMANTICS AND ONTOLOGIES (ONLINE), vol. 12 (issue 1), pp. 35-46
DOI: 10.1504/ijmso.2017.087692DOI: 10.1504/ijmso.2017.10008654Project(s): PARTHENOS
Metrics:
See at:
CNR IRIS
| ISTI Repository
| www.inderscience.com
| International Journal of Metadata Semantics and Ontologies
| International Journal of Metadata Semantics and Ontologies
| CNR IRIS
| CNR IRIS
2017
Journal article
Open Access
DanteSources: a digital library for studying Dante Alighieri's primary sources
Bartalesi Lenzi V, Meghini C, Metilli D, Andriani P, Tavoni MWe present DanteSources, a focused Digital Library that aims at building innovative services supporting scholars in creating, evolving and consulting a digital encyclopaedia of Dante Alighieri's works. DanteSources is endowed with Web services that allow extracting and visualizing data about Dante Alighieri's primary sources, i.e. other authors' works which Dante referred to in his own works. The heart of the digital library is a knowledge base built on an ontology that was developed in the RDF/S language, representing Dante's works and the knowledge about them, extracted from some authoritative commentaries. Finally, on top of this graph, we developed DanteSources, which allows users to extract and display the knowledge stored in the knowledge base in the form of charts and tables. The methodology and the tool we developed are easily reusable to represent the knowledge about primary sources of other authors of the Italian or the international literature.Source: UMANISTICA DIGITALE, pp. 119-128
DOI: 10.6092/issn.2532-8816/7250Metrics:
See at:
CNR IRIS
| ISTI Repository
| Umanistica Digitale
| CNR IRIS
2018
Conference article
Open Access
A Software Architecture for Narratives
Meghini C, Bartalesi V, Metilli D, Benedetti FThe current Digital Libraries (DLs) usually return as answer of a user's query a ranked list of the resources included in the DLs but no semantic relation among the resources are reported. Using the Semantic Web technologies it is possible to improve these search functionalities introducing narratives as new search method. As narratives we intend semantic networks of events that are linked to the objects of the DLs and are endowed with a set of semantic relations that connect an event to another. These semantic networks may help the users to obtain a more complete knowledge on the subject of their searches. In this paper, we present a software architecture for building narratives in order to introduce them in DLs. Our architecture is composed of several tools (automatic and semi-automatic tools) for creating, storing and visualizing narratives. When possible, we reused open source components already available on-line, and for the software we developed, we freely distribute it for research aims.Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE (PRINT), pp. 23-29. Udine, Italy, 25-26 January 2018
DOI: 10.1007/978-3-319-73165-0_3Project(s): PARTHENOS
Metrics:
See at:
CNR IRIS
| link.springer.com
| ISTI Repository
| doi.org
| CNR IRIS
| CNR IRIS
2019
Journal article
Open Access
Introducing narratives in Europeana: a case study
Meghini C, Bartalesi V, Metilli D, Benedetti FWe present a preliminary study to introduce narratives as a first-class functionality in digital libraries. The general idea is to enrich those libraries with semantic networks of events providing a meaningful contextualisation of the digital libraries' objects. More specific motivations are presented through a set of use cases by different actors who would benefit from using narratives for different purposes. Then, we consider a specific digital library, Europeana, the largest European digital library in the cultural heritage domain. We discuss how the Europeana Data Model could be extended for representing narratives, and we introduce an ontology for narratives. We also present a semi-automatic tool, which, on the basis of the ontology, supports the creation and visualisation of narratives, and we show how the tool has been employed to create a narrative of the life of the painter Gustav Klimt as a case study. In particular, we focus our attention on the functionality of the tool that allows extracting and proposing to the user specific digital objects for each event of the narrative.Source: INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, vol. 29 (issue 1), pp. 7-16
DOI: 10.2478/amcs-2019-0001Metrics:
See at:
International Journal of Applied Mathematics and Computer Science
| International Journal of Applied Mathematics and Computer Science
| International Journal of Applied Mathematics and Computer Science
| CNR IRIS
| ISTI Repository
| www.amcs.uz.zgora.pl
| CNR IRIS
2019
Conference article
Open Access
Populating narratives using Wikidata events: an initial experiment
Metilli D, Bartalesi V, Meghini C, Aloia NThe study presented in this paper is part of our research aimed at improving the search functionalities of current Digital Libraries using formal narratives. Narratives are intended as sequences of events. We present the results of an initial experiment to detect and extract implicit events from the Wikidata knowledge base in order to construct a narrative in a semi-automatic way. Wikidata contains many historical entities, but comparably few events. The reason is that most events in Wikidata are represented in an implicit way, e.g. by listing a date of birth instead of having an event of type "birth". For this reason, we decided to generate what we call the Wikidata Event Graph (WEG), i.e. the graph of implicit events found in Wikidata. We performed an initial experiment taking as case study the narrative of the life of Italian poet Dante Alighieri. Only one event of the life of Dante is explicitly represented in Wikidata as instance of the class Q1190554 Occurrence. Using the WEG, we were able to automatically detect 31 more events of Dante's life that were present in Wikidata in an implicit way.Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE (PRINT), pp. 159-166. Pisa, Italy, 31 Juanry - 01 February 2019
DOI: 10.1007/978-3-030-11226-4_13DOI: 10.5281/zenodo.2555042DOI: 10.5281/zenodo.2555043DOI: 10.5281/zenodo.1489713DOI: 10.5281/zenodo.1489714Metrics:
See at:
ZENODO
| ZENODO
| ZENODO
| ZENODO
| CNR IRIS
| link.springer.com
| ISTI Repository
| ISTI Repository
| zenodo.org
| doi.org
| CNR IRIS
| CNR IRIS
| CNR IRIS