Michele Ciletti

124 Followers
315 Following
38 Posts

Student and researcher in Digital Humanities @ Unifg, bass player and huge fan of open access, orecchiette, haiku, myths and technology used for social good.

Currently working on text mining, classics, computational literary studies and EdTech.

ResearchGatehttps://www.researchgate.net/profile/Michele-Ciletti
Websitehttps://mmm.page/micheleciletti/me
The project will deliver new open data and a training resource on how to integrate LLMs in linguistic research. Many thanks to H2IOSC and its funders for supporting this work!

I'm glad to share that I have been awarded an H2IOSC Transnational Mobility Grant for a research stay at King’s College London! @kingsdh

During the visit, I will work with Barbara McGillivray and Andrea Farina to develop a semi-automatic semantic annotation pipeline for perception verbs in Latin and Ancient Greek, while also testing these methods on Italian.

Excited to speak at "AI and Digital Humanities: Methodological Approaches, Theories and Methods" at the University of Siena on November 5!

I’ll discuss how historical linguistics can partner with AI, presenting a case study on Latin prosody. Check out the full program and follow the conference online: https://www.unisi.it/unisilife/eventi/ai-and-digital-humanities-methodological-approaches-theories-and-methods

This week I had a lot of fun in Cagliari at #clicit2025!

I presented a paper titled "Veras Audire Et Reddere Voces: A Corpus of Prosodically-Correct Latin Poetic Audio from Large-Language-Model TTS". Check out the pre-proceedings here: https://clic2025.unica.it/pre-proceedings/

Excited to be in Cagliari for CLiC-it 2025! I'll be presenting a paper on text-to-speech LLMs and Latin prosody - check out the full program! https://clic2025.unica.it/technical-program/
Poster, slides and video presentation are all available on Zenodo: https://doi.org/10.5281/zenodo.16421715
Next week, I will be attending #ACL2025 to present a paper on generating prosodically-accurate Latin poetry recordings with LLMs. Pretty excited to be there for the first time! Check it out: https://aclanthology.org/2025.acl-srw.48/
Prompting the Muse: Generating Prosodically-Correct Latin Speech with Large Language Models

Michele Ciletti. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop). 2025.

ACL Anthology
I had a lot of fun presenting a paper on tracing temporal changes in communities during transition periods via network analysis - starting from a case study on a WWII-era newspaper - at #DH2025. My slides are available on Zenodo for anyone interested! https://doi.org/10.5281/zenodo.16097984
Many interesting insights and approaches were discussed this afternoon - and a new special collection on language data reuse was announced! Learn more here: https://openhumanitiesdata.metajnl.com/ #DH2025
Today’s #highlight for me on the last day of #DH2025? Luca Giovannini presenting his "Modest Proposal for Operationalizing Dramatic Texts". He proposes drama vectorization not to simplify plays, but rather to continue formalist morphological thinking using computational tools. 🎭📊 #CLS #drama