Beyond cognacy

2025-07-02

AI Summary

Traditional historical linguistics relies on expert-annotated cognate sets, resulting in data sparsity, high annotation cost, and poor scalability across language families. This paper proposes a fully automated phylogenetic inference method that requires no manual etymological annotation. First, unsupervised cognate clustering extracts lexical correspondences; second, single-character and concept-based features are modeled, and multi-sequence alignment is performed via pair-HMMs; finally, phylogenetic trees are reconstructed using likelihood-based methods. By eliminating dependence on expert cognate judgments, the approach overcomes a key bottleneck and significantly enhances cross-family scalability. Experiments demonstrate that our method outperforms baselines in language classification accuracy and typological variation prediction, while exhibiting stronger phylogenetic signal consistency. It establishes a reproducible, generalizable paradigm for large-scale global language evolution studies.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Machine Learning: Evolutionary Learning
• Cognitive Modeling & Cognitive Systems: Analogy

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Computational phylogenetics has become an established tool in historical linguistics, with many language families now analyzed using likelihood-based inference. However, standard approaches rely on expert-annotated cognate sets, which are sparse, labor-intensive to produce, and limited to individual language families. This paper explores alternatives by comparing the established method to two fully automated methods that extract phylogenetic signal directly from lexical data. One uses automatic cognate clustering with unigram/concept features; the other applies multiple sequence alignment (MSA) derived from a pair-hidden Markov model. Both are evaluated against expert classifications from Glottolog and typological data from Grambank. Also, the intrinsic strengths of the phylogenetic signal in the characters are compared. Results show that MSA-based inference yields trees more consistent with linguistic classifications, better predicts typological variation, and provides a clearer phylogenetic signal, suggesting it as a promising, scalable alternative to traditional cognate-based methods. This opens new avenues for global-scale language phylogenies beyond expert annotation bottlenecks.

Problem

• Automating phylogenetic signal extraction from lexical data
• Comparing MSA-based inference to traditional cognate methods
• Scaling language phylogenies beyond expert-annotated cognate sets

Innovation

• Automated cognate clustering with unigram features
• Multiple sequence alignment via hidden Markov model
• Phylogenetic signal comparison for language classification