Principal Component Analysis as a Sanity Check for Bayesian Phylolinguistic Reconstruction

Yugo Murawaki


Abstract
Bayesian approaches to reconstructing the evolutionary history of languages rely on the tree model, which assumes that these languages descended from a common ancestor and underwent modifications over time. However, this assumption can be violated to different extents due to contact and other factors. Understanding the degree to which this assumption is violated is crucial for validating the accuracy of phylolinguistic inference. In this paper, we propose a simple sanity check: projecting a reconstructed tree onto a space generated by principal component analysis. By using both synthetic and real data, we demonstrate that our method effectively visualizes anomalies, particularly in the form of jogging.
Anthology ID:
2024.lrec-main.1138
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
12999–13013
Language:
URL:
https://aclanthology.org/2024.lrec-main.1138
DOI:
Bibkey:
Cite (ACL):
Yugo Murawaki. 2024. Principal Component Analysis as a Sanity Check for Bayesian Phylolinguistic Reconstruction. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12999–13013, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Principal Component Analysis as a Sanity Check for Bayesian Phylolinguistic Reconstruction (Murawaki, LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1138.pdf