Comanche

COMANCHE proposes to transfer and adapt recent algorithms of representation learning from deep learning to model the evolution of word meaning, by comparing them with theories on language acquisition and the diachrony of languages. At the crossroad between machine learning, psycholinguistics and historical linguistics, this project intends to validate or revise some of these theories, but also to bring out models computational models that are less data and computation hungry by resorting to new inductive biases inspired by these disciplines.