Neural Proto-Language Reconstruction

arXiv:2404.15690v1 Announce Type: new
Abstract: Proto-form reconstruction has been a painstaking process for linguists. Recently, computational models such as RNN and Transformers have been proposed to automate this process. We take three different approaches to improve upon previous methods, including data augmentation to recover missing reflexes, adding a VAE structure to the Transformer model for proto-to-language prediction, and using a neural machine translation model for the reconstruction task. We find that with the additional VAE structure, the Transformer model has …

abstract arxiv augmentation automate computational cs.cl cs.lg data form language prediction process proto rnn transformer transformer model transformers type vae