BibTeX

@article{borin-etal-2021-bird's-309082,
	title        = {A bird’s-eye view on South Asian languages
through LSI: Areal or genetic relationships?},
	abstract     = {We present initial exploratory work on illuminating the long-standing question of areal versus genealogical connections in South Asia using computational data visualization tools. With respect to genealogy, we focus on the subclassification of Indo-Aryan, the most ubiquitous language family of South Asia. The intent here is methodological: we explore computational methods for visualizing large datasets of linguistic features, in our case 63 features from 200 languages representing four language families of South Asia, coming out of a digitized version of Grierson’s Linguistic Survey of India. To this dataset we apply phylogenetic software originally developed in the context of computational biology for clustering the languages and displaying the clusters in the form of networks. We further explore multiple correspondence analysis as a way of illustrating how linguistic feature bundles correlate with extrinsically defined groupings of languages (genealogical and geographical). Finally, map visualization of combinations of linguistic features and language genealogy is suggested as an aid in distinguishing genealogical and areal features. On the whole, our results are in line with the conclusions of earlier studies: Areality and genealogy are strongly intertwined in South Asia, the traditional lower-level subclassification of Indo-Aryan is largely upheld, and there is a clearly discernible areal east–west divide cutting across language families.},
	journal      = {Journal of South Asian Languages and Linguistics},
	author       = {Borin, Lars and Saxena, Anju and Virk, Shafqat and Comrie, Bernard},
	year         = {2021},
	volume       = {7},
	number       = {2},
	pages        = {151--185},
}