Open access
2026
AraBERT-Based Semantic Lexicon Induction for Arabic Academic Text: Query Expansion, Document Clustering, and Classification
Type-level representations derived from AraBERT are exploited to compute dense, L2-normalized word embeddings and apply GPU-accelerated cosine similarity search to retrieve up to three semantically induced neighbors per vocabulary item in the ARPD.
Ahmad Al Smadi, Yasser Allaham, Lara Rbabah
· IEEE Access · 0 citations