@inproceedings{alvarez-mellado-2020-annotated,
    title = "An Annotated Corpus of Emerging Anglicisms in {S}panish Newspaper Headlines",
    author = "Alvarez-Mellado, Elena",
    booktitle = "Proceedings of the The 4th Workshop on Computational Approaches to Code Switching",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2020.calcs-1.1",
    pages = "1--8",
    abstract = "The extraction of anglicisms (lexical borrowings from English) is relevant both for lexicographic purposes and for NLP downstream tasks. We introduce a corpus of European Spanish newspaper headlines annotated with anglicisms and a baseline model for anglicism extraction. In this paper we present: (1) a corpus of 21,570 newspaper headlines written in European Spanish annotated with emergent anglicisms and (2) a conditional random field baseline model with handcrafted features for anglicism extraction. We present the newspaper headlines corpus, describe the annotation tagset and guidelines and introduce a CRF model that can serve as baseline for the task of detecting anglicisms. The presented work is a first step towards the creation of an anglicism extractor for Spanish newswire.",
    language = "English",
    ISBN = "979-10-95546-66-5",
}