# Neural Proto-Language Reconstruction

arXiv: https://arxiv.org/abs/2404.15690 · HTML: https://mlsanity.com/paper/2404.15690/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 15 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Builds on (most cited first, 3 of 3)

- [Applying the Transformer to Character-level Transduction](https://mlsanity.com/paper/2005.10213/) (2020)
- [Ab Antiquo: Neural Proto-language Reconstruction](https://mlsanity.com/paper/1908.02477/) (2019)
- [A New Framework for Fast Automated Phonological Reconstruction Using Trimmed Alignments and Sound Correspondence Patterns](https://mlsanity.com/paper/2204.04619/) (2022)

## Abstract (arXiv)

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 a better performance on the WikiHan dataset, and the data augmentation step stabilizes the training.