Mercer Times

In his final year at Princeton, Fernando Avilés-García applied an innovative approach to analyze Dante Alighieri’s "Divine Comedy" by building an artificially intelligent tool. “The Comedy has been egregiously underserved by modern language models, considering how weighty a text it is,” said Avilés-García, a computer science major with a certificate from the Department of French and Italian. “This project let me overlap my love of solving puzzles through code with my passion for Italian.”

“It’s one of the most original senior theses I’ve read at Princeton through the years — and I’ve read some great senior theses,” said Gaetana Marrone-Puglia, a professor of French and Italian who has taught at Princeton since 1988. “Fernando brought a computer model to texts that normally are in the hands of medievalists. It’s a perfect marriage of science and humanities.”

The final product, titled “Divining language: Unearthing medieval Italian through natural language processing (NLP),” earned Avilés-García departmental high honors and the inaugural Lucio Caputo Senior Thesis Prize “for an outstanding thesis on the literature, language, culture, economy, history, politics or society of Italy.” Christiane Fellbaum, his thesis adviser and lecturer with the rank of professor in computer science, linguistics, and the Council of the Humanities at Princeton, commented on his achievement: “He has created a tool that I think will be beneficial for the Italian literature community and will inspire future studies.”

Avilés-García initially experienced imposter syndrome during his early programming courses at Princeton but overcame these feelings as he progressed. Reflecting on this period, he said: “I really got hooked on that feeling of ‘I’m making things!’” By his sophomore year, he declared computer science as his major despite initial doubts about his coding background.

Natalia Ermolaev, executive director of the Center for Digital Humanities at Princeton, noted that many undergraduates naturally bridge humanities and AI. She stated: “This happens all the time at Princeton because we have so many computer science majors that secretly love classics or Italian literature or medieval architecture.”

Born in Mexico City and raised in Basking Ridge, New Jersey, Avilés-García grew up bilingual in English and Spanish and developed a love for Italian during summers in Sicily. His adviser Simone Marchesi suggested analyzing Dante’s "Divine Comedy," written between 1308 and 1321 in an archaic Tuscan dialect. Marchesi remarked: “Dante is the father of the Italian language, but his text is not standard Italian.” Avilés-García collaborated with programmers from the University of Pisa to train his model to parse medieval Italian.

Avilés-García's work revealed intriguing patterns when quantifying words frequently appearing together in "The Comedy." He found unexpected connections between words related to light (shine, star) and darkness (night) rather than traditional associations with love-related terms. This led him to new insights about Dante’s depiction of Hell as devoid of stars and love.

Marchesi confirmed the significance of Avilés-García's findings: “What he has found is real, I would say, and not self-evident.” He added that most scholars have focused on stars as navigational tools while Avilés-García identified a broader conceptual link between their absence and Hell.

Looking forward to using this AI model in future research endeavors, Marchesi expressed optimism about continued collaboration: “Someone who is a Princetonian once is a Princetonian forever,” he said.