@InProceedings{milajevs:2017:BUCC,
  author    = {Milajevs, Dmitrijs},
  title     = {Toward a Comparable Corpus of Latvian, Russian and English Tweets},
  booktitle = {Proceedings of the 10th Workshop on Building and Using Comparable Corpora},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  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.},
  url       = {http://www.aclweb.org/anthology/W17-2505}
}