FBFederico Boschetti

Federico Boschetti

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Federico Boschetti has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Reviving Legacy WordNet-Like Resources: MariTerm and ItalWordNet Renewal Through Mutual Expansion and Plug-In Links

    by Lucia Galiero, Federico Boschetti, Riccardo Del Gratta, Angelo Mario Del Grosso, Monica Monachini

    This paper presents a case study in legacy lexical resource renewal through mutual expansion and cross-resource linking, involving two Italian lexical databases: ItalWordNet (IWN), a general-purpose WordNet, and MariTerm, a specialized maritime terminology resource. Both resources, developed in the early 2000s, face challenges due to outdated formats, incomplete cross-referencing, and structural inconsistencies despite overlapping coverage. Through a semi-automatic pipeline combining similarity scoring and manual validation, we expanded IWN with 1,160 maritime-specific semantic relations and created 363 new synsets, i.e, sets of synonymous terms sharing semantic properties and contextual interchangeability. At the same time, the pipeline created 751 mapping nodes from MariTerm to IWN and 759 in the opposite direction. The new MariTerm version, now featured in an official CLARIN repository, contains 27 new synsets with 38 new lemmas and comprehensive cross-resource integration. The process still revealed critical challenges in reusing legacy data: structural inconsistencies, missing metadata and duplicate entries. We demonstrate how strategic expansion and linking not only preserved valuable linguistic knowledge but enhanced both resources’ utility for specialized and general-purpose applications. The renewed databases exemplify how legacy resources can be revitalized through systematic reuse methodologies and straightforward rule-based algorithms, benefiting from reciprocal enrichment while achieving modern standards of interoperability and sustainability.

  • Open Access

    Filologia virgiliana e codici digitalizzati: esperienza d’uso di servizi

    by Federico Boschetti, Francesca Boldrer

    Sono presentate le attività seminariali e di laboratorio che hanno coinvolto studenti dell’Università di Macerata, con particolare attenzione all’applicazione di tecniche di Layout Analysis, Handwritten Text Recognition e correzione manuale su campioni estratti da due manoscritti virgiliani. Viene discusso inoltre il contesto di collaborazione fra Università, CNR e Infrastrutture di Ricerca.

  • Open Access

    Making digital scholarly editions based on Domain Specific Languages

    by Simone Zenzaro, Federico Boschetti, Angelo Mario Del Grosso

    Over time textual scholars have refined the methods to represent the codicological, paleographic, philological, and other aspects relevant for the study of documents (i.e. material objects) and texts (i.e. immaterial entities). According to a general trend observable along the last four centuries not only in the STEM disciplines but in every domain of knowledge, the specific languages adopted by the scholars to represent the objects of their studies evolved improving both in precision and concision. It suffices to compare critical apparatuses sampled in a wide temporal span for a quick verification. Indeed, it is surprising that in the digital age the collective effort of the scholars to optimize the representation and the transmission of their domain-specific knowledge has been penalized and verbose solutions (e.g. through XML encoding) or, on the contrary, non-verbal solutions (e.g. through GUIs) have been adopted. The classical scholarly practices represent a valuable synthesis of centuries of knowledge in specific domains, so it is paramount to preserve such standards. Another relevant aspect is the ability to endow the scholars with a methodology that retains and expands all the expressiveness needed to deal with the text challenges. The digital counterpart has also produced and established standards. The methodology based on Domain Specific Languages (DSLs)1 requires the definition of a formal language derived from the well established ecdotic practices that are already a set of editorial conventions and convey the analytical representation of the information in the text. For example, critical apparatuses are already a quasi-formal domain language and are therefore suitable for the definition of a DSL via a context-free grammar. The next step is to feed a rich text editing tool with the DSL in order to enable the corresponding language interpretation. The result is to provide scholars with a reusable and modular computer-assisted environment that eases the creation and analysis of the scholarly edition. At the same time, computational functionalities empower the process with multimodal search, classification and prediction strategies of philological phenomena, consistent and systematic coherence checks of the editorial conventions and errors, analysis and recall of information deduced from the context or from external sources (e.g. vocabulaires and corpora) via machine learning algorithms, etc. Moreover, a fully collaborative environment allows scholars to contribute to an ongoing cooperative edition. In this context it is possible to widen the access to the text to scholars, students, practitioners, and volunteers. Finally, this approach ensures the compatibility with the standards accepting toward and producing from the DSL a compliant representation of the edited text that can interoperate with the digital humanities community and the galaxy of related tools. The DSL-based methodology is well known and exploited mostly outside the scholarly editing domain. Being a formal language, a DSL has its roots in the language theory and the first attempts saw the effort to use them to describe natural languages. That path has been proved to be infeasible due to the ambiguity of natural languages but this is not the case with the philological domain. The markdown language is an example of a commonly used DSL, but its scope is a general purpose description of the structure of a document. Thus it is not meant to describe philological textual phenomena. Leiden+2, instead, is a good example of the application of a DSL in the domain of traditional papyrology conventions. Adopting a DSL for the scholarly editing process allows the philologist to remain close to the classical practices while enabling the possibility to improve the process with the digital capabilities. The only constraint enforced by this approach is the ambiguity elimination. 1 For further details see S. Zenzaro, A. M. Del Grosso, F. Boschetti,,G. Ranocchia. 2022. “Verso la definizione di criteri per valutare soluzioni di scholarly editing digitale: il caso d’uso GreekSchools”, in proceedings of AIUCD2022. Lecce. DOI:10.6092/unibo/amsacta/6848 2 Cfr https://papyri.info/docs/leiden_plus

  • Top Cited Papers

    CATMuS Medieval: A Multilingual Large-Scale Cross-Century Dataset in Latin Script for Handwritten Text Recognition and Beyond

    by Thibault Clérice, Ariane Pinche, Malamatenia Vlachou-Efstathiou, Alix Chagué, Jean-Baptiste Camps, Matthias Gille Levenson, Olivier Brisville-Fertin, Federico Boschetti, Franz Fischer, Michael Gervers, et al.


  • Open Access

    Domain-Specific Languages for Epigraphy: the Case of ItAnt

    by Federico Boschetti, Luca Rigobianco, Valeria Quochi

    This contribution illustrates how the definition of a Domain-Specific Language can support the activities of epigraphists and historical linguists. It presents and discusses a method and technological solution, based on Domain-Specific Languages, for facilitating scholars in digitally representing the available knowledge of archaic languages and cultures. This is achieved by increasing the human readability of the encoded data without sacrificing compliance with standard models and formats. The work is framed within the context of an Italian National collaborative research project devoted to the study of the languages and cultures of ancient Italy. The platform developed within this project offers an interesting use case and motivation for experimenting with Domain-Specific Languages for the creation of necessary digital critical editions of the inscriptions relevant for these languages. After explaining the definition process of the DSL grammar, we finally test the applicability of the DSL grammar to five example inscriptions in the Faliscan language.

    • 1 December 2022
    • Published by HAL in HAL
    Open Access

    EpiSearch. Identifying Ancient Inscriptions in Epigraphic Manuscripts

    by Lorenzo Calvelli, Federico Boschetti, Tatiana Tommasi

    Hundreds of thousands of Greek and Latin inscriptions from the Roman world have survived until today, scattered across all continents and spanning fifteen centuries of ancient history. Epigraphic documents constitute an essential source of evidence for our knowledge of the ancient world and can be considered an authentic repository of big data. However, a significant number of inscriptions have not been preserved in their material form. In fact, their texts can only be recovered thanks to the socalled epigraphic manuscripts: crucial documents consisting of handwritten transcriptions made in post-classical times. In spite of their importance, these manuscripts have seldom received sufficient scholarly attention, and use of state-of-the-art digital tools for the study of the transcribed inscriptions is completely lacking. EpiSearch is a pilot project that explores the application of technologies deployed in the field of the Digital Humanities to recover the epigraphic evidence found in epigraphic manuscripts. Each step of the project is intended as a proof of concept, in view of a future large-scale and collaborative research plan. As a sample, we chose an epigraphic manuscript composed by the Venetian ecclesiastical antiquarian Giovanni Antonio Astori (1672-1743) and preserved in the Marciana Library in Venice: Marc. Lat. XIV, 200 (4336). Within this broader framework, this article focuses on the characteristics of Astori's manuscript and on the possibilities offered by Handwritten Text Recognition (HTR) to improve its study. The application of HTR to epigraphic manuscripts is a challenging task, given the nature and graphic layout of these texts. However, our research shows that, even with some limits, HTR technologies can be used successfully, especially to map legacy manual transcriptions on the manuscript facsimile and to improve the layout analysis of the document. These results will be used for one of the final goals of the EpiSearch project, that is the design of an Open Access web application for allowing users to browse the manuscript, which will be visually annotated and connected to the main online resources for digital epigraphy.

  • Open Access

    L’annotazione di testi storico-letterari al tempo dei social media

    by CNR-ILC of Pisa & VeDPH Ca’ Foscari Venezia, Federico Boschetti, Angelo Grosso, Cnr-Ilc Of Pisa

  • L’annotazione di testi storico-letterari al tempo dei social media

    by CNR-ILC of Pisa & VeDPH Ca’ Foscari Venezia, Federico Boschetti, Angelo Grosso, Cnr-Ilc Of Pisa

  • L’annotazione di testi storico-letterari al tempo dei social media

    by Federico Boschetti, Angelo Mario Del Grosso

    The annotation of historical and literary texts in the age of social media


  • Restructuring a Taxonomy of Literary Themes and Motifs for More Efficient Querying

    by Fahad Khan, Silvia Arrigoni, Federico Boschetti, Francesca Frontini

    In this paper we describe ongoing work in the restructuring of a tagset originally organised as a taxonomy and used to annotate literary themes and motifs in a corpus of classical works of poetry from a number of different traditions. We show how such a tagset can be rendered more efficient and useful through the appropriation of ideas and techniques from lexical semantics and ontology design. The newly redesigned tagset is described with examples showing how the new design is much more expressive than the old taxonomy; furthermore, an example query is described in order to demonstrate how more refined semantic searches can be carried using the new version of the taxonomy. The final result is, we hope, a resource that will be useful not only for the specific project for which it was developed but one that is well-designed and well-documented enough to be of use for other similar semantic annotation tasks.