# Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference

arXiv: https://arxiv.org/abs/2609.05262 · HTML: https://mlsanity.com/paper/2609.05262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 59 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding](https://mlsanity.com/paper/2109.04380/) (2021)
- [Learning Language Representations for Typology Prediction](https://mlsanity.com/paper/1707.09569/) (2017)
- [Probing Multilingual BERT for Genetic and Typological Signals](https://mlsanity.com/paper/2011.02070/) (2020)
- [Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations](https://mlsanity.com/paper/2004.14923/) (2020)
- [URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base](https://mlsanity.com/paper/2409.18472/) (2024)
- [Continuous multilinguality with language vectors](https://mlsanity.com/paper/1612.07486/) (2016)
- [What do Language Representations Really Represent?](https://mlsanity.com/paper/1901.02646/) (2019)
- [Global-scale phylogenetic linguistic inference from lexical resources](https://mlsanity.com/paper/1802.06079/) (2018)
- [Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics?](https://mlsanity.com/paper/1804.05416/) (2018)
- [LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization](https://mlsanity.com/paper/2401.06034/) (2024)
- [Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter](https://mlsanity.com/paper/2501.14491/) (2025)
- [Language Embeddings Sometimes Contain Typological Generalizations](https://mlsanity.com/paper/2301.08115/) (2023)
- [Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging](https://mlsanity.com/paper/2503.19979/) (2025)
- [Found in Translation: Reconstructing Phylogenetic Language Trees from Translations](https://mlsanity.com/paper/1704.07146/) (2017)
- [Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: 'UFAL Submission to the SIGTYP 2020 Shared Task](https://mlsanity.com/paper/2010.03920/) (2020)
- [Generating Feature Vectors from Phonetic Transcriptions in Cross-Linguistic Data Formats](https://mlsanity.com/paper/2405.04271/) (2024)
- [data2lang2vec: Data Driven Typological Features Completion](https://mlsanity.com/paper/2409.17373/) (2024)
- [Are Sounds Sound for Phylogenetic Reconstruction?](https://mlsanity.com/paper/2402.02807/) (2024)
- [Beyond cognacy](https://mlsanity.com/paper/2507.03005/) (2025)
- [Self-Supervised Borrowing Detection on Multilingual Wordlists](https://mlsanity.com/paper/2512.01713/) (2025)

## Abstract (arXiv)

Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two factors: the labor-intensive manual annotation of cognacy judgments required for character-based methods and the substantial computational cost of inference on large datasets. This paper introduces a fully self-supervised contrastive learning framework that learns lexical representations directly from raw IPA-transcribed wordlists, without requiring cognacy annotations, alignments, or additional expert input. The model employs a dual contrastive objective: a word-level loss that organizes phonetically similar forms into a coherent space, and an auxiliary language-level loss that encourages the lexical space to reflect broader phonological properties of languages. From the resulting word representations, pairwise language distances are derived and used to infer a global phylogenetic tree of 3,399 language varieties. The inferred tree achieves a generalized quartet distance (GQD) to the Glottolog reference tree competitive with multiple baselines, while requiring only minutes of computation on a standard notebook GPU. Furthermore, the same representations capture diachronic concept stability: variance in pairwise distances across languages yields stability rankings that correlate significantly with established rankings. Ablation studies confirm that both the language-level objective and the use of phonetic feature vectors improved the inferred trees topology with regards to GQD. The framework thus provides a computationally efficient and fully automatic alternative for large-scale phylogenetic inference and offers a unified representation supporting downstream analyses at both the language and concept level.