Whether or not several Creole languages which developed during the early modern period can be considered genetic descendants of European languages has been the subject of intense debate. This is in large part due to the absence of evidence of intermediate forms. This work introduces a new open corpus, the Molyé corpus, which combines stereotypical representations of three kinds of language variation in Europe with early attestations of French-based Creole languages across a period of 400 years. It is intended to facilitate future research on the continuity between contact situations in Europe and Creolophone (former) colonies.

In this study, we propose to evaluate the use of deep learning methods for semantic classification at the sentence level to accelerate the process of corpus building in the field of humanities and linguistics, a traditional and time-consuming task. We introduce a novel corpus comprising around 2500 sentences spanning from 300 BCE to 900 CE including sexual semantics (medical, erotica, etc.). We evaluate various sentence classification approaches and different input embedding layers, and show that all consistently outperform simple token-based searches. We explore the integration of idiolectal and sociolectal metadata embeddings (centuries, author, type of writing), but find that it leads to overfitting. Our results demonstrate the effectiveness of this approach, achieving high precision and true positive rates (TPR) of respectively 70.60% and 86.33% using HAN. We evaluate the impact of the dataset size on the model performances (420 instead of 2013 training samples), and show that, while our models perform worse, they still offer a high enough precision and TPR, even without MLM, respectively 69% and 51%. Given the result, we provide an analysis of the attention mechanism as a supporting added value for humanists in order to produce more data.

Literature works may present many autonomous or semi-autonomous units, such as poems for the first or chapter for the second. We make the hypothesis that such cuts in the text’s flow, if not taken care of in the way we process text, have an impact on the application of the distributional hypothesis. We test this hypothesis with a large 20M tokens corpus of Latin works, by using text files as a single unit or multiple “autonomous” units for the analysis of selected words. For groups of rare words and words specific to heavily segmented works, the results show that their semantic space is mostly different between both versions of the corpus. For the 1000 most frequent words of the corpus, variations are important as soon as the window for defining neighborhood is larger or equal to 10 words.