Hello, I’m Ema — a research scientist at DHLAB (Digital Humanities Laboratory), EPFL in Lausanne, Switzerland.

I have a background in both computer science and art, which shapes the way I approach research, creativity, and problem-solving. While my main focus today is on natural language processing (NLP) and historical document analysis, I also studied video and photography — two practices that continue to influence how I see patterns, identity, and representation.

Outside of research, I’m usually at a metal festival, camping, or watching movies and series (always) and sometimes reading non-fantasy books.

Generally, I value listening, clarity, and thoughtful action — I believe in speaking with purpose, without unnecessary repetition, and following through. Harsh this sentence, ain’t it? Yes, my humor is Bukowski-like at times, George Carlin-like at others — dry, blunt, and a little irreverent, but usually funny in its honesty.

My background

I received my Ph.D. in Computer Science in 2018 from Paris-Saclay University, France, specializing in natural language processing (NLP). My thesis proposed several neural network architectures for extracting events from unstructured text.

Before that, I earned an M.Sc. in Software Engineering and a B.Sc. in Computer Science from the Alexandru I. Cuza University, Faculty of Computer Science, Iași, Romania. In parallel, I also pursued my interest in the arts, completing both an M.A. and B.A. in Visual Arts (video & photography) at the George Enescu National University of Arts, Iași, Romania.

During my Ph.D., I spent three years at CEA, List (Laboratory for Integration of Systems and Technology) and LIMSI (now LISN), both in Orsay, France. I then worked for a year as a research engineer at the LAL (Linear Accelerator Laboratory) within the Paris-Saclay Center for Data Science. My work there focused on NLP applications in French law (case outcome prediction) and fake news detection.

From 2017 to 2019, I joined Teklia as a machine learning scientist, where I developed technologies for digitised and historical document understanding, including handwriting recognition, article separation, and named entity recognition.

In 2020, I returned to academia as a postdoctoral researcher at the University of La Rochelle, in the L3i (IT, Image and Interaction) Laboratory, where I worked until the end of 2022.

My main research interest is information extraction — entities, relations, and events — from digitised documents, at the intersection of NLP, machine learning, and cultural data.