Automated identification of borrowings in multilingual wordlists

Although lexical borrowing is an important aspect of language evolution, there have been few attempts to automate the identification borrowings in datasets. Moreover, none solutions which proposed so far identify across multiple languages. This study proposes a new method for task and tests it on newly compiled large comparative dataset 48 South-East Asian languages from Southern China. The yields very promising results, while conceptually straightforward easy apply. makes approach perfect candidate computer-assisted exploratory studies contact areas.