EUVIMEDEUVIMED entdecken
Crossref

Topic Clustering of English-uUkrainian Text Corpora Using Multilingual Embeddings

Pavlyshenko B, Stasiuk M

Artificial Intelligence · 30.03.2026 · 31 (AI.2026.31(1)) · 35-47

DOI: 10.15407/jai2026.01.035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence, erschienen am 30.03.2026. Verfasst von Pavlyshenko B und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates the impact of multilingual sentence-embedding models on unsupervised thematic clustering of a balanced bilingual corpus comprising English and Ukrainian documents. While modern embedding architectures project texts from multiple languages into a shared semantic space, it remains unclear how effectively different models preserve geometrically separable thematic structure suitable for clustering. A balanced dataset of 1,404 documents across four high-level thematic domains, namely History, Culture, Science, and Technology was constructed using a high-confidence zero-shot labeling procedure. Three multilingual sentence embedding models LaBSE, paraphrase-xlm-r-multilingual-v1, and paraphrase-multilingual-mpnet-base-v2 were evaluated in combination with three clustering approaches: KMeans, Agglomerative Hierarchical Clustering, and Fuzzy C-Means. Visual analysis using UMAP projections and quantitative evaluation via intrinsic (Silhouette, Calinski-Harabasz, Davies-Bouldin) and extrinsic (Adjusted Rand Index, Normalized Mutual Information) metrics reveal that clustering performance is primarily determined by the geometric properties of the embedding space rather than by the choice of clustering algorithm. LaBSE produces the most stable and well-separated thematic regions, achieving the highest agreement with ground truth categories. The paraphrase-xlm-r model exhibits reduced thematic separability, while the multilingual MPNet variant demonstrates intermediate behavior with stronger performance under hierarchical clustering. Across all models, English and Ukrainian documents remain interwoven within thematic regions, confirming effective cross-lingual alignment. However, the degree of semantic separability varies significantly between embedding architectures. The findings indicate that representation quality plays a dominant role in unsupervised thematic analysis of bilingual corpora. Embedding model selection is therefore a more impactful factor than clustering strategy when analyzing cross-lingual semantic structure

Zitieren

APA

B, P., & M, S. (2026). Topic Clustering of English-uUkrainian Text Corpora Using Multilingual Embeddings. Artificial Intelligence, 31(AI.2026.31(1)), 35-47. https://doi.org/10.15407/jai2026.01.035

Vancouver

B P, M S. Topic Clustering of English-uUkrainian Text Corpora Using Multilingual Embeddings. Artificial Intelligence. 2026;31(AI.2026.31(1)):35-47. doi:10.15407/jai2026.01.035

BibTeX
@article{B2026,
  author = {B, Pavlyshenko and M, Stasiuk},
  title = {Topic Clustering of English-uUkrainian Text Corpora Using Multilingual Embeddings},
  journal = {Artificial Intelligence},
  year = {2026},
  volume = {31},
  number = {AI.2026.31(1)},
  pages = {35--47},
  doi = {10.15407/jai2026.01.035}
}
Kostenlos starten →