Myrsini Ioannou

Software Engineer @ GlossAPI / GFOSS–EELLAK

Speaker's Bio

Myrsini Ioannou studied Applied Mathematics and Physical Sciences at the National Technical University of Athens (NTUA) and holds a Master’s degree in Sound and Music Computing from Universitat Pompeu Fabra in Barcelona.
She has worked as a Data Scientist and joined the glossAPI team in March 2025 as a Software Engineer, focusing on the development and optimization of natural language processing technologies.

Myrsini Ioannou studied Applied Mathematics and Physical Sciences at the National Technical University of Athens (NTUA) and holds a Master’s degree in Sound and Music Computing from Universitat Pompeu Fabra in Barcelona.
She has worked as a Data Scientist and joined the glossAPI team in March 2025 as a Software Engineer, focusing on the development and optimization of natural language processing technologies.

dataset cards EELLAK GFOSS GitHub Greek datasets Hugging Face Large Language Models (LLM) Natural Language Processing (NLP) open data reproducibility transparency

GlossAPI

Fri 21 Nov 2025 • Community presence • 14:15 (CET) • Basic, Intermediate
Open Space

GlossAPI is an open‑source Python library and technical infrastructure to create, curate, and publish AI‑ready Greek datasets. At our Open Space stand, we’ll showcase documented datasets hosted on Hugging Face and the reproducible preprocessing workflows that produce them. Visitors will see how academics, students, and practitioners can contribute new corpora or reuse existing data in Natural Language Processing (NLP, Natural Language Processing) and Large Language Models (LLM, Large Language Models) applications. We’ll run short offline demos, share dataset cards, and provide links to repositories (Hugging Face / GitHub) and a collaboration form.

Focus: transparent pipelines, licensing clarity, and practical reusability—lowering friction for those building or evaluating Greek AI.

Goal: grow a community around open standards and rigorous documentation so Greek‑language AI becomes more accessible, ethical, and reproducible.

GFOSS

Fri 21 Nov 2025 • Community presence • 14:15 (CET)
Auditorium

GFOSS (Open Technologies Alliance)

dataset cards EELLAK GFOSS GitHub Greek datasets Hugging Face Large Language Models (LLM) Natural Language Processing (NLP) open data reproducibility transparency

GlossAPI: Open infrastructure for AI‑ready Greek datasets

Fri 21 Nov 2025 • GlossAPI, Presentation • 15:15 (CET) • Basic, Intermediate
Open Space

GlossAPI is an open‑source Python library and technical infrastructure to create, curate, and publish AI‑ready Greek datasets. At our Open Space stand, we’ll showcase documented datasets hosted on Hugging Face and the reproducible preprocessing workflows that produce them. Visitors will see how academics, students, and practitioners can contribute new corpora or reuse existing data in Natural Language Processing (NLP, Natural Language Processing) and Large Language Models (LLM, Large Language Models) applications. We’ll run short offline demos, share dataset cards, and provide links to repositories (Hugging Face / GitHub) and a collaboration form.

Focus: transparent pipelines, licensing clarity, and practical reusability—lowering friction for those building or evaluating Greek AI.

Goal: grow a community around open standards and rigorous documentation so Greek‑language AI becomes more accessible, ethical, and reproducible.

GFOSS

Sat 22 Nov 2025 • Community presence • 11:25 (CET)
Auditorium

GFOSS (Open Technologies Alliance)

Lottery – Closing

Open Award

Gold Sponsor: Yodeck

Scaling product development at Orfium using Domain Driven Design and Team Topologies

Lottery

Coffee Break