Background image

LostMa

navigating the currents of culture

What is LostMa?

A digital humanities research project that blends AI, complexity science, and philological expertise to unravel the mysteries behind the deviation from pure chance of a text's transmission.

We are funded by the European Research Council (ERC) for five years, 2024-2029. Our offices are in the Campus Condorcet's Hôtel à projets and we are hosted by the École nationale des chartes in Paris, France.

Data

A big milestone of the LostMa project is to assemble and publish a multilingual corpus of textual traditions. A narrative's inclusion in the corpus is defined by the following criteria:

What

Describes a hero or epic adventure.

How

First circulated in manuscript form.

When

First copies were written before the printing press.

Where

Circulated within Western Europe.

Learn more about the corpus, database, and data model.

Methods

...

Output

Scientific articles, conference presentatations, and other publications.

Publications

Scientific articles, conference presentatations, and other publications.

Releases

Versions of datasets, models, and software released for download.

Events

Conferences, hackathons, and other in-person events.

People

LostMa / French Corpus

Meet the Team

Our core team is responsible for the project's milestones and the French-language part of the corpus.

Jean-Baptiste Camps
Project Leader
Kelly Christensen
Data Architect
Ulysse Godreau
Postdoc
Théo Moins
AI Engineer
Beatriz Tadeo Fuica
Administrator
International

Meet Our Collaborators

We collaborate with specialists in various literary traditions. They contribute data from different language communities to broaden the scope of the project's corpus.

Elisabeth de Bruijn
Middle Dutch Corpus
Katarzyna Kapitan
Old Norse Corpus
Mike Kestemont
Middle Dutch Corpus
Carolina Macedo
Iberian Corpus
Remco Sleiderink
Middle Dutch Corpus
Cecile Vermaas
Middle Dutch Corpus