@inproceedings{3827c5b4fa4e430cb4293dc99edb1e30,
title = "Ab Antiquo: Neural Proto-language Reconstruction",
abstract = "Historical linguists have identified regularities in the process of historic sound change. The comparative method utilizes those regularities to reconstruct proto-words based on observed forms in daughter languages. Can this process be efficiently automated? We address the task of proto-word reconstruction, in which the model is exposed to cognates in contemporary daughter languages, and has to predict the proto word in the ancestor language. We provide a novel dataset for this task, encompassing over 8,000 comparative entries, and show that neural sequence models outperform conventional methods applied to this task so far. Error analysis reveals a variability in the ability of neural model to capture different phonological changes, correlating with the complexity of the changes. Analysis of learned embeddings reveals the models learn phonologically meaningful generalizations, corresponding to well-attested phonological shifts documented by historical linguistics.",
author = "Carlo Meloni and Shauli Ravfogel and Yoav Goldberg",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021 ; Conference date: 06-06-2021 Through 11-06-2021",
year = "2021",
month = jan,
day = "1",
doi = "10.18653/v1/2021.naacl-main.353",
language = "American English",
series = "NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "4460--4473",
booktitle = "NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics",
address = "United States",
}