Automating Sound Change Prediction for Phylogenetic Inference: A Tukanoan Case Study
This work addresses the challenge of automating phylogenetic inference for linguists, offering a semi-automated approach that reduces reliance on expert annotations.
The authors tackled the problem of automating linguistic phylogenetic inference by training a neural network to predict sound changes between protoforms and modern languages, replacing expert input in part of a parsimony-based algorithm. In experiments on Tukanoan languages, their method achieved a Generalized Quartet Distance of 0.12 from expert-annotated trees, outperforming other semi-automated baselines.
We describe a set of new methods to partially automate linguistic phylogenetic inference given (1) cognate sets with their respective protoforms and sound laws, (2) a mapping from phones to their articulatory features and (3) a typological database of sound changes. We train a neural network on these sound change data to weight articulatory distances between phones and predict intermediate sound change steps between historical protoforms and their modern descendants, replacing a linguistic expert in part of a parsimony-based phylogenetic inference algorithm. In our best experiments on Tukanoan languages, this method produces trees with a Generalized Quartet Distance of 0.12 from a tree that used expert annotations, a significant improvement over other semi-automated baselines. We discuss potential benefits and drawbacks to our neural approach and parsimony-based tree prediction. We also experiment with a minimal generalization learner for automatic sound law induction, finding it comparably effective to sound laws from expert annotation. Our code is publicly available at https://github.com/cmu-llab/aiscp.