Work

Linguistic Influence on Multidimensional Word Embeddings: Analysis of Ten Languages

Year: 2026

Type: article

Abstract: Understanding how linguistic typology shapes multilingual embeddings is important for cross-lingual NLP. We examine static MUSE word embedding for ten diverse languages (English, Russian, Chinese, Arabic, Indonesian, German, Lithuanian, Hindi, Tajik and Persian). Using pairwise cosine distances, Random Forest classification, and UMAP visualization, we find that language identity and script type largely determine embedding clusters, with morphological complexity affecting cluster compactness and lexical overlap connecting clusters. The Random Forest model predicts language labels with high accuracy (≈98%), indicating strong language-specific patterns in embedding space. These results highlight script, morphology, and lexicon as key factors influencing multilingual embedding structures, informing linguistically aware design of cross-lingual models.

Source: Computation

DOI: 10.3390/computation14010016

Authors: Anna V. Aleshina, Andrey L. Bulgakov, Yanliang Xin, Larisa S. Skrebkova

Institutions: Lomonosov Moscow State University, Moscow Center of Fundamental and Applied Mathematics

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,172

Funders: Moscow Center of Fundamental and Applied Mathematics, Lomonosov Moscow State University