用机器学习识别苏拉威西语中非主流词汇，发现其无统一底层语言痕迹。
Phonological Fossils: Machine Learning Detection of Non-Mainstream Vocabulary in Sulawesi Basic Lexicon
- 结合词源剔除与XGBoost模型，从音韵特征识别非主流词汇
- 438个候选词中266个高置信度非主流词，占比达26.5%
- 揭示长词、辅音簇多等音韵特征，适合语言演化研究者
许多苏拉威西南岛语的基本词汇包含无法还原为原始形式的音韵异常形式，其是否源于南岛语前底层或独立创新尚未经计算验证。本研究结合规则型词源剔除与基于26个音韵特征的XGBoost分类器，分析来自六个苏拉威西语言的1,357个词。通过词源剔除与原始南岛语对照，识别出438个候选非主流词（占26.5%）。分类器在区分继承词与非主流词时达到AUC=0.763，揭示其音韵指纹：词长更长、辅音簇更多、声门塞音频率更高、南岛语前缀更少。跨方法一致性（Cohen's kappa=0.61）确认266个高置信度候选词。聚类分析未发现一致词族（轮廓系数=0.114；跨语言同源检验p=0.569），无证据支持单一前南岛语层。对16个额外语言的应用显示地理模式：苏拉威西语言预测非主流率均值为0.606，高于西印度尼西亚语言的0.393。结果表明，音韵机器学习可补充传统比较法检测非主流词汇层，但提醒不可将音韵异常视为共享底层语言的证据。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。