@inproceedings{gezmu-etal-2018-contemporary,
    title = "Contemporary {A}mharic Corpus: Automatically Morpho-Syntactically Tagged {A}mharic Corpus",
    author = {Gezmu, Andargachew Mekonnen  and
      Seyoum, Binyam Ephrem  and
      Gasser, Michael  and
      N{\"u}rnberger, Andreas},
    editor = "Machonis, Peter  and
      Barreiro, Anabela  and
      Kocijan, Kristina  and
      Silberztein, Max",
    booktitle = "Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing",
    month = aug,
    year = "2018",
    address = "Santa Fe, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W18-3809/",
    pages = "65--70",
    abstract = "We introduced the contemporary Amharic corpus, which is automatically tagged for morpho-syntactic information. Texts are collected from 25,199 documents from different domains and about 24 million orthographic words are tokenized. Since it is partly a web corpus, we made some automatic spelling error correction. We have also modified the existing morphological analyzer, HornMorpho, to use it for the automatic tagging."
}