# Approaching Reflex Predictions as a Classification Problem Using Extended Phonological Alignments

arXiv: https://arxiv.org/abs/2205.09570 · HTML: https://mlsanity.com/paper/2205.09570/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 56 references that are in the map.
- First posted on arXiv 19 May 2022.

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

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [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)
- [Computational Historical Linguistics](https://mlsanity.com/paper/1805.08099/) (2018)

## Abstract (arXiv)

This work describes an implementation of the "extended alignment" (or "multitiers") approach for cognate reflex prediction, submitted to "Prediction of Cognate Reflexes" shared task. Similarly to List2022d, the technique involves an automatic extension of sequence alignments with multilayered vectors that encode informational tiers on both site-specific traits, such as sound classes and distinctive features, as well as contextual and suprasegmental ones, conveyed by cross-site referrals and replication. The method allows to generalize the problem of cognate reflex prediction as a classification problem, with models trained using a parallel corpus of cognate sets. A model using random forests is trained and evaluated on the shared task for reflex prediction, and the experimental results are presented and discussed along with some differences to other implementations.