Extracting English Lexical Borrowings from Spanish Newswire

Abstract

In this work, we present: (1) a corpus of European Spanish newswire annotated with anglicisms; (2) a sequence labeling model to extract English lexical borrowings (or anglicisms) from Spanish newswire; and (3) a tracking corpus of anglicism usage in the Spanish press.

Publication
Proceedings of the Society for Computation in Linguistics (SCiL 2021): Vol. 4 , Article 41