# Transformed Protoform Reconstruction

arXiv: https://arxiv.org/abs/2307.01896 · HTML: https://mlsanity.com/paper/2307.01896/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 36 references that are in the map.
- First posted on arXiv 4 Jul 2023.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Ab Antiquo: Neural Proto-language Reconstruction](https://mlsanity.com/paper/1908.02477/) (2019)
- [Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics?](https://mlsanity.com/paper/1804.05416/) (2018)
- [A New Framework for Fast Automated Phonological Reconstruction Using Trimmed Alignments and Sound Correspondence Patterns](https://mlsanity.com/paper/2204.04619/) (2022)
- [Neural Unsupervised Reconstruction of Protolanguage Word Forms](https://mlsanity.com/paper/2211.08684/) (2022)
- [In search of isoglosses: continuous and discrete language embeddings in Slavic historical phonology](https://mlsanity.com/paper/2005.13575/) (2020)

## Built on by (most cited first, 2 of 2)

- [PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics](https://mlsanity.com/paper/2505.23126/) (2025)
- [Phonetic Reconstruction of the Consonant System of Middle Chinese via Mixed Integer Optimization](https://mlsanity.com/paper/2502.04625/) (2025)

## Abstract (arXiv)

Protoform reconstruction is the task of inferring what morphemes or words appeared like in the ancestral languages of a set of daughter languages. Meloni et al. (2021) achieved the state-of-the-art on Latin protoform reconstruction with an RNN-based encoder-decoder with attention model. We update their model with the state-of-the-art seq2seq model: the Transformer. Our model outperforms their model on a suite of different metrics on two different datasets: their Romance data of 8,000 cognates spanning 5 languages and a Chinese dataset (Hou 2004) of 800+ cognates spanning 39 varieties. We also probe our model for potential phylogenetic signal contained in the model. Our code is publicly available at https://github.com/cmu-llab/acl-2023.