Researchers have developed a computational framework to analyze the diachronic semantic change in the Sinhala language, spanning from the 13th to the 20th century. The study utilized both static embeddings (Word2Vec, FastText) and contextualized embeddings from a fine-tuned Llama-3.1-8B model. Findings indicate that semantic drift is not uniform but is significantly influenced by a smaller subset of high-impact contextual instances, rather than a gradual, widespread shift. AI
IMPACT Provides a framework for diachronic analysis in low-resource languages, potentially improving historical linguistics tools.
RANK_REASON Academic paper detailing a new computational framework for analyzing semantic change in a low-resource language. [lever_c_demoted from research: ic=1 ai=1.0]
- Bidirectional Semantic Impact Pruning
- fastText
- Llama-3.1:8b
- Nevidu Jayatilleke
- Orthogonal Procrustes problem
- Similarity Matrix Based Alignment
- Sinhala
- Word2Vec
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →