L'eredità biblica nella letteratura cristiana antica in latino: un contributo alla mappatura delle relazioni intertestuali tramite sentence embeddings

Autori

  • Anna Mambelli University of Modena and Reggio Emilia
  • Laura Bigoni University of Bologna
  • Davide Dainese University of Bologna
  • Fabio Tutrone University of Palermo
  • Davide Caffagni University of Modena and Reggio Emilia
  • Federico Cocchi University of Modena and Reggio Emilia
  • Marco Zanella University of Padua
  • Marcella Cornia University of Modena and Reggio Emilia
  • Rita Cucchiara University of Modena and Reggio Emilia

DOI:

https://doi.org/10.60923/issn.2532-8816/22160

Parole chiave:

Bibbie latine, patristica latina, intertestualità, sentence embeddings basati su BERT, IRCDL2025

Abstract

Questo studio presenta una metodologia interdisciplinare per l’individuazione dei riferimenti biblici nella letteratura patristica latina, attraverso un intreccio innovativo di rigore filologico e tecniche di Natural Language Processing (NLP). Focalizzandosi su uno dei più significativi commentari cristiani antichi alla Bibbia, il De Genesi ad litteram di Agostino d’Ippona, e sul suo rapporto con i testi biblici in latino (in particolare la Vulgata di Gerolamo e le versioni precedenti), la ricerca introduce un sistema di classificazione dei riferimenti intertestuali basato su token, arricchito da annotazioni semantiche e supportato dalla piattaforma INCEpTION. La prima sezione dell'articolo illustra come questo sistema di classificazione numerica comprenda corrispondenze esatte, forme flesse, radici, sinonimi e altri tipi di parallelismi semantici (qui definiti “strutture”), catturando un ampio spettro di similarità testuale. Per migliorare il recupero automatico di queste connessioni intertestuali, alcuni modelli linguistici per il latino basati su BERT vengono sottoposti a fine-tuning, integrando tecniche di contrastive learning e hard negative mining. Nella seconda sezione, i risultati sperimentali mostrano che i modelli sottoposti a fine-tuning ottengono risultati nettamente migliori rispetto ai modelli di base a vari livelli di similarità testuale. Questo lavoro mette in evidenza l’utilità dei modelli computazionali nel superare la tradizionale dicotomia tra citazioni esplicite e allusioni implicite, accogliendo molteplici sfumature intermedie di similarità e offrendo un approccio scalabile allo studio dell’intertestualità negli scritti antichi.

Riferimenti bibliografici

[1] Sternberg, Meir. 1982. "Proteus in Quotation-Land: Mimesis and the Forms of Reported Discourse." In Poetics Today 3 (2): 107–156.

[2] Daise, Michael A., and Dorota Hartman, eds. 2022. Creative Fidelity, Faithful Creativity: The Reception of Jewish Scripture in Early Judaism and Christianity. Napoli: UniorPress.

[3] Lupieri, Edmondo F., and Louis Painchaud, eds. 2024. "Who Is Sitting on Which Beast?" Interpretative Issues in the Book of Revelation. Turnhout: Brepols.

[4] Bons, Eberhard, and Daniela Scialabba, eds., in collaboration with Anna Mambelli. 2020–. Historical and Theological Lexicon of the Septuagint (HTLS). 4 vols. Tübingen: Mohr Siebeck.

[5] Klie, Jan-Christoph, Michael Bugert, Beto Boullosa, Richard Eckart de Castilho, and Iryna Gurevych. 2018. "The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation." In Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations.

[6] Allenbach, Jean. 1967. Étapes, moyens et méthode d’analyse pour la constitution du Fichier microphotographique des citations de l’Écriture chez les Pères. Strasbourg: Université de Strasbourg.

[7] Allenbach, Jean, André Benoît, Daniel A. Bertrand, et al., eds. 1975. Biblia Patristica: index des citations et allusions bibliques dans la littérature patristique. 5 vols. Vol. 1, Des origines à Clément d’Alexandrie et Tertullien. Paris: CNRS.

[8] Emadi, Samuel. 2015. "Intertextuality in New Testament Scholarship: Significance, Criteria, and the Art of Intertextual Reading." In Currents in Biblical Research 14 (1): 8–23.

[9] Dainese, Davide, and Anna Mambelli. 2023–2024. "Intertestualità tra Bibbie e antichi commentari cristiani: l’esempio di simul nel De Genesi ad litteram di Agostino." In Lexicon Philosophicum: International Journal for the History of Texts and Ideas 11: 39–65.

[10] Caffagni, Davide, Federico Cocchi, Anna Mambelli, Fabio Tutrone, Marco Zanella, Marcella Cornia, and Rita Cucchiara. 2025. "Benchmarking BERT-based Models for Latin: A Case Study on Biblical References in Ancient Christian Literature." In Proceedings of the 21st Conference on Information and Research Science Connecting to Digital and Library Science.

[11] Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. "Attention Is All You Need." In Advances in Neural Information Processing Systems.

[12] Devlin, Jacob, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding." In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

[13] Liu, Yinhan, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. "RoBERTa: A Robustly Optimized BERT Pretraining Approach." arXiv preprint arXiv:1907.11692.

[14] Sanh, Victor, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. "DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter." In Advances in Neural Information Processing Systems.

[15] Bamman, David, and Patrick J. Burns. 2020. "Latin BERT: A Contextual Language Model for Classical Philology." arXiv preprint arXiv:2009.10053.

[16] Ströbel, Patrick B. 2022. "RoBERTa Base Latin Cased v1." https://huggingface.co/pstroe/roberta-base-latin-cased.

[17] Riemenschneider, Frederick, and Anette Frank. 2023. "Exploring Large Language Models for Classical Philology." In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.

[18] Weber, Robert, and Roger Gryson, eds. 52007. Biblia Sacra iuxta Vulgatam Versionem, Stuttgart: Deutsche Bibelgesellschaft (R. Weber, 11969).

[19] Sabatier, Pierre, ed. 1743–1751. Bibliorum Sacrorum latinae versiones antiquae seu Vetus Italica. 3 vols. Reims: Reginaldus Florentain.

[20] Fischer, Bonifatius, Roger Gryson, Walter Thiele, et al., eds. 1949–. Vetus Latina: Die Reste der altlateinischen Bibel nach Petrus Sabatier neu gesammelt und herausgegeben von der Erzabtei Beuron. Freiburg i.B.: Herder.

[21] Huskey, Samuel J. 2019. "The Digital Latin Library: Cataloging and Publishing Critical Editions of Latin Texts." In Monica Berti, ed., Digital Classical Philology: Ancient Greek and Latin in the Digital Revolution, 19–34. Berlin-Boston: De Gruyter.

[22] Kauhanen, Tuukka, and Hannu Kalavainen. 2020. "Automated Semantic Tagging of the Göttingen Septuagint Apparatus." In A Journal of Biblical Textual Criticism 25: 145–147.

[23] Zycha, Joseph. 1894. Sancti Aureli Augustini De Genesi ad litteram libri duodecim: eiusdem libri capitula. De Genesi ad litteram imperfectus liber. Locutionum in Heptateuchum libri septem. Pragae & Vindobonae & Lipsiae: Tempsky & Freyta.

[24] Horstmann, Jan, Christian Lück, and Immanuel Normann. 2023. "Systems of Intertextuality: Towards a Formalization of Text Relations for Manual Annotation and Automated Reasoning." In Digital Humanities Quarterly 17 (3): 1–74.

[25] Trillini, Regula Hohl, and Sixta Quassdorf. 2010. "A ‘Key to All Quotations’? A Corpus-Based Parameter Model of Intertextuality." In Literary and Linguistic Computing 25 (3): 269–286.

[26] Andrews, Tara L., and Caroline Macé, eds. 2014. Analysis of Ancient and Medieval Texts and Manuscripts: Digital Approaches. Turnhout: Brepols.

[27] Tomazzoli, Gaia. 2022. "Intertextuality in Dante’s ‘Commedia’: Hypermedia Dante Network." In Bibliotheca Dantesca 5: 308–311.

[28] Compagnon, Antoine. 1979. La Seconde Main, ou le travail de la citation. Paris: Éditions du Seuil.

[29] Rose, Paula J. 2013. A Commentary on Augustine’s De cura pro mortuis gerenda: Rhetoric in Practice. Leiden-Boston: Brill.

[30] Houghton, Hugh A.G. 2023. "The Earliest Latin Translations of the Bible." In Hugh A.G. Houghton, ed., The Oxford Handbook of the Latin Bible, 6–7. Oxford and New York: Oxford University Press.

[31] Fröhlich, Uwe, ed. 1995–1998. Epistula ad Corinthios I. Fasc. 1–3 [Vetus Latina: Die Reste der altlateinischen Bibel nach Petrus Sabatier neu gesammelt und herausgegeben von der Erzabtei Beuron]. Freiburg i.B.: Herder.

[32] Taylor, John H., ed. 1982. St. Augustine: The Literal Meaning of Genesis. Vol. 2, Books 7–12. Mahwah: Paulist Press.

[33] Walsh, Patrick G., ed. 2017. Augustine: De Civitate Dei (The City of God), Books XIII & XIV. Liverpool: Liverpool University Press.

[34] Houghton, Hugh A.G. 2008. Augustine’s Text of John: Patristic Citations and Latin Gospel Manuscripts. Oxford and New York: Oxford University Press.

[35] Capone, Alessandro. 2010. "Review of Augustine’s Text of John: Patristic Citations and Latin Gospel Manuscripts, by Hugh A.G. Houghton." In Bryn Mawr Classical Review 2010.04.29.

[36] Cornia, Marcella, Matteo Stefanini, Lorenzo Baraldi, Massimiliano Corsini, and Rita Cucchiara. 2020. "Explaining Digital Humanities by Aligning Images and Textual Descriptions." In Pattern Recognition Letters 129: 166–172.

[37] Sarto, Sara, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2024. "Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training." arXiv preprint arXiv:2410.07336.

[38] Caffagni, Davide, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2025. "Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39] Oord, Aaron van den, Yazhe Li, and Oriol Vinyals. 2018. "Representation Learning with Contrastive Predictive Coding." arXiv preprint arXiv:1807.03748.

[40] Izacard, Gautier, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. "Unsupervised Dense Information Retrieval with Contrastive Learning." In Transactions on Machine Learning Research.

[41] Neelakantan, Arvind, Tao Xu, Raul Puri, Alec Radford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, Johannes Heidecke, Pranav Shyam, Boris Power, Tyna Eloundou Nekoul, Girish Sastry, Gretchen Krueger, David Schnurr, Felipe Petroski Such, Kenny Hsu, Madeleine Thompson, Tabarak Khan, Toki Sherbakov, Joanne Jang, Peter Welinder, and Lilian Weng. 2022. "Text and Code Embeddings by Contrastive Pre-Training." arXiv preprint arXiv:2201.10005.

[42] Chen, Ting, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. "A Simple Framework for Contrastive Learning of Visual Representations." In Proceedings of the 37th International Conference on Machine Learning.

[43] Khosla, Prannay, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. "Supervised Contrastive Learning." In Advances in Neural Information Processing Systems.

[44] Radford, Alec, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. "Learning Transferable Visual Models From Natural Language Supervision." In Proceedings of the 38th International Conference on Machine Learning.

[45] Faghri, Fartash, David J. Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives." In Proceedings of the British Machine Vision Conference 2018.

[46] Kalantidis, Yannis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel, and Diane Larlus. 2020. "Hard Negative Mixing for Contrastive Learning." In Advances in Neural Information Processing Systems.

[47] Zhan, Jingtao, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021. "Optimizing Dense Retrieval Model Training with Hard Negatives." In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.

[48] Conneau, Alexis, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. "Unsupervised Cross-lingual Representation Learning at Scale." In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.

[49] Kingma, Diederik P., and Jimmy Ba. 2015. "Adam: A Method for Stochastic Optimization." In Proceedings of the 3rd International Conference for Learning Representations.

[50] Mambelli, Anna, and Marcello Costa. 2025. “Exploring the uBIQUity of Biblical Texts: Tradition and Innovation in the Ancient and Digital Worlds.” In The Digital Turn in Religious Studies. Research, Services, Infrastructures. Eds. Alberto Melloni and Francesca Cadeddu. Göttingen: Vandenhoeck & Ruprecht, 149-176.

[51] Dainese, Davide, Laura Bigoni, and Marco Zanella. 2025. “Resilient Septuagint Between Borges and Asimov: A State-of-the-Art Case of Ubiquity.” In The Digital Turn in Religious Studies. Research, Services, Infrastructures. Eds. Alberto Melloni and Francesca Cadeddu. Göttingen: Vandenhoeck & Ruprecht, 177-206.

Downloads

Pubblicato

2026-02-02

Come citare

Mambelli, A., Bigoni, L., Dainese, D., Tutrone, F., Caffagni, D., Cocchi, F., … Cucchiara, R. (2026). L’eredità biblica nella letteratura cristiana antica in latino: un contributo alla mappatura delle relazioni intertestuali tramite sentence embeddings. Umanistica Digitale, 10(22), 157–186. https://doi.org/10.60923/issn.2532-8816/22160