@inproceedings{milajevs-2017-toward,
    title = "Toward a Comparable Corpus of {L}atvian, {R}ussian and {E}nglish Tweets",
    author = "Milajevs, Dmitrijs",
    editor = "Sharoff, Serge  and
      Zweigenbaum, Pierre  and
      Rapp, Reinhard",
    booktitle = "Proceedings of the 10th Workshop on Building and Using Comparable Corpora",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W17-2505/",
    doi = "10.18653/v1/W17-2505",
    pages = "26--30",
    abstract = "Twitter has become a rich source for linguistic data. Here, a possibility of building a trilingual Latvian-Russian-English corpus of tweets from Riga, Latvia is investigated. Such a corpus, once constructed, might be of great use for multiple purposes including training machine translation models, examining cross-lingual phenomena and studying the population of Riga. This pilot study shows that it is feasible to build such a resource by collecting and analysing a pilot corpus, which is made publicly available and can be used to construct a large comparable corpus."
}