Phonological Fossils: Machine Learning Detection of Non-Mainstream Vocabulary in Sulawesi Basic Lexicon

• URL: http://arxiv.org/abs/2604.00023v1
• Date: Wed, 11 Mar 2026 05:23:53 GMT
• Title: Phonological Fossils: Machine Learning Detection of Non-Mainstream Vocabulary in Sulawesi Basic Lexicon
• Abstract summary: Using 1,357 forms from six Sulawesi languages, we identify 438 candidate substrate forms (26.5%) through cognate subtraction and Proto-Austronesian cross-checking.<n>An XGBoost classifier trained on 26 phonological features distinguishes inherited from non-mainstream forms with AUC=.763.<n> clustering yields no coherent word families, providing no evidence for a single pre-Austronesian language layer.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Basic vocabulary in many Sulawesi Austronesian languages includes forms resisting reconstruction to any proto-form with phonological patterns inconsistent with inherited roots, but whether this non-conforming vocabulary represents pre-Austronesian substrate or independent innovation has not been tested computationally. We combine rule-based cognate subtraction with a machine learning classifier trained on phonological features. Using 1,357 forms from six Sulawesi languages in the Austronesian Basic Vocabulary Database, we identify 438 candidate substrate forms (26.5%) through cognate subtraction and Proto-Austronesian cross-checking. An XGBoost classifier trained on 26 phonological features distinguishes inherited from non-mainstream forms with AUC=0.763, revealing a phonological fingerprint: longer forms, more consonant clusters, higher glottal stop rates, and fewer Austronesian prefixes. Cross-method consensus (Cohen's kappa=0.61) identifies 266 high-confidence non-mainstream candidates. However, clustering yields no coherent word families (silhouette=0.114; cross-linguistic cognate test p=0.569), providing no evidence for a single pre-Austronesian language layer. Application to 16 additional languages confirms geographic patterning: Sulawesi languages show higher predicted non-mainstream rates (mean P_sub=0.606) than Western Indonesian languages (0.393). This study demonstrates that phonological machine learning can complement traditional comparative methods in detecting non-mainstream lexical layers, while cautioning against interpreting phonological non-conformity as evidence for a shared substrate language.

Related papers

• Most over-representation of phonological features in basic vocabulary disappears when controlling for spatial and phylogenetic effects [4.7379911264912185]
  We test the robustness of a recent study on sound symbolism of basic vocabulary concepts which analyzed245 languages.<n>New results show that most of the previously observed patterns are not robust, and in fact many patterns disappear completely when adding the genealogical and areal controls.
  arXiv  Detail & Related papers  (2025-12-08T13:24:53Z)
• Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically [58.019484208091534]
  Cross-lingual alignment in pretrained language models (LMs) has enabled efficient transfer in text-based LMs.<n>It remains an open question whether findings and methods from text-based cross-lingual alignment apply to speech.
  arXiv  Detail & Related papers  (2025-05-26T07:21:20Z)
• Unsupervised Classification of English Words Based on Phonological Information: Discovery of Germanic and Latinate Clusters [4.6432459304786375]
  Cross-linguistically, native words and loanwords follow different phonological rules.<n>We show that the Germanic-Latinate distinction in the English lexicon is learnable from the phonotactic information of individual words.
  arXiv  Detail & Related papers  (2025-04-16T05:20:08Z)
• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  We train and evaluate neural networks directly as binary classifiers of strings.<n>We provide results on a variety of languages across the Chomsky hierarchy for three neural architectures.<n>Our contributions will facilitate theoretically sound empirical testing of language recognition claims in future work.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• Are Sounds Sound for Phylogenetic Reconstruction? [41.85920785319125]
  We test, for the first time, the performance of sound-based versus cognate-based approaches to phylogenetic reconstruction. Our results show that phylogenies reconstructed from lexical cognates are topologically closer, by approximately one third with respect to the generalized quartet distance on average.
  arXiv  Detail & Related papers  (2024-02-05T08:35:33Z)
• Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models [84.86942006830772]
  We conjecture that multilingual pre-trained models can derive language-universal abstractions about grammar. We conduct the first large-scale empirical study over 43 languages and 14 morphosyntactic categories with a state-of-the-art neuron-level probe.
  arXiv  Detail & Related papers  (2022-05-04T12:22:31Z)
• A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space [61.18554842370824]
  In cross-lingual language models, representations for many different languages live in the same space. We compute a task-based measure of cross-lingual alignment in the form of bitext retrieval performance. We examine a range of linguistic, quasi-linguistic, and training-related features as potential predictors of these alignment metrics.
  arXiv  Detail & Related papers  (2021-09-13T21:05:37Z)
• Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties [77.2347265289855]
  We focus on phoneme recognition using Allosaurus, a method for multilingual recognition based on phonetic annotation. To evaluate in a challenging real-world scenario, we curate phone recognition datasets for Bukusu and Saamia, two varieties of the Luhya language cluster of western Kenya and eastern Uganda. We find that fine-tuning of Allosaurus, even with just 100 utterances, leads to significant improvements in phone error rates.
  arXiv  Detail & Related papers  (2021-04-04T15:07:55Z)
• A phonetic model of non-native spoken word processing [40.018538874161756]
  We train a computational model of phonetic learning, which has no access to phonology, on either one or two languages. We first show that the model exhibits predictable behaviors on phone-level and word-level discrimination tasks. We then test the model on a spoken word processing task, showing that phonology may not be necessary to explain some of the word processing effects observed in non-native speakers.
  arXiv  Detail & Related papers  (2021-01-27T11:46:21Z)
• Deciphering Undersegmented Ancient Scripts Using Phonetic Prior [31.707254394215283]
  Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges. We propose a model that handles both of these challenges by building on rich linguistic constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian)
  arXiv  Detail & Related papers  (2020-10-21T15:03:52Z)
• Phonotactic Complexity and its Trade-offs [73.10961848460613]
  This simple measure allows us to compare the entropy across languages. We demonstrate a very strong negative correlation of -0.74 between bits per phoneme and the average length of words.
  arXiv  Detail & Related papers  (2020-05-07T21:36:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.