Tag
The paper presents an inductive framework for learning language-independent concept embeddings from cross-linguistic colexification networks combined with textual concept descriptions, enabling embeddings for unseen concepts and correlating well with cross-linguistic similarity measures.
This paper validates the use of diachronic word embeddings for measuring semantic change in Sanskrit, demonstrating high accuracy in recovering philologically attested shifts despite the language's low-resource and complex morphology.
This paper presents multi-agent simulations of the emergence of morphological alternation patterns (like 'go/went') in language, using an AI Historical Linguist (LLM-driven) to evaluate plausibility of evolved morphologies against real languages.
A deep learning framework is developed to analyze grammatical gender evolution from Latin to Romance languages, focusing on low-resource historical settings using lexical and contextual analysis.
This paper analyzes the Huitongguanxi Huayiyiyu, a series of multilingual glossaries from the Ming dynasty, as a structured cross-linguistic transcription system that used Chinese characters to represent non-Chinese languages, revealing how Chinese phonological categories were flexibly extended for phonetic approximation.