En dépit de leur qualité certaine, les ressources et outils disponibles pour l’analyse du français d’Ancien Régime ne sont plus à même de répondre aux enjeux de la recherche en linguistique et en littérature pour cette période. Après avoir précisément défini le cadre chronologique retenu, nous présentons les corpus mis à disposition et les résultats obtenus avec eux pour plusieurs tâches de TAL fondamentales à l’étude de la langue et de la littérature.

Language models for historical states of language are becoming increasingly important to allow the optimal digitisation and analysis of old textual sources. Because these historical states are at the same time more complex to process and more scarce in the corpora available, specific efforts are necessary to train natural language processing (NLP) tools adapted to the data. In this paper, we present our efforts to develop NLP tools for Early Modern French (historical French from the 16th to the 18th centuries). We present the FREEMmax corpus of Early Modern French and D'AlemBERT, a RoBERTa-based language model trained on FREEMmax. We evaluate the usefulness of D'AlemBERT by fine-tuning it on a part-of-speech tagging task, outperforming previous work on the test set. Importantly, we find evidence for the transfer learning capacity of the language model, since its performance on lesser-resourced time periods appears to have been boosted by the more resourced ones. We release D'AlemBERT and the open-sourced subpart of the FREEMmax corpus.

We investigate the creation of a 17th c. French literary corpus. We present the main options regarding available standards, the training data we created and the efficiency of the models produced for OCR, spelling normalisation and lemmatisation – always with open-source solutions. We also present our encoding choices and the global logic of a corpus designed as a virtuous circle, enhancing automatically the tools that are used for its construction.

Because manuscripts are lost, burned, torn apart or thrown away, it is as complex as crucial to know how many of them still exist for any philologist preparing an edition. Thanks to a (semi-)automatic and fully-open source workflow, we have extracted, structured and annotated hundreds of manuscript sale catalogues published in 19th c. Paris. The obtained level of granularity allows us not only to reconcile different sales of a single item sold multiple times, but also to identify if the manuscript is now kept in a library. Using Sevigne as a test case, we were able to calculate that c. 1% of her manuscripts still has to be found because they are circulating on the private market. All the data we produced remain available for similar research on other authors.

We investigate the creation of a 17th c. French literary corpus. We present the main options regarding available standards, the training data we created and the efficiency of the models produced for OCR, spelling normalisation and lemmatisation - always with open-source solutions. We also present our encoding choices and the global logic of a corpus designed as a virtuous circle, enhancing automatically the tools that are used for its construction.