Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1362553, author = {Štromajerová, Adéla and Baisa, Vít and Blahuš, Marek}, address = {Brno}, booktitle = {RASLAN 2016 Recent Advances in Slavonic Natural Language Processing}, keywords = {parallel corpora; comparable corpora; Wikipedia}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, isbn = {978-80-263-1095-2}, pages = {3-8}, publisher = {Tribun EU}, title = {Between Comparable and Parallel: English-Czech Corpus from Wikipedia}, url = {https://nlp.fi.muni.cz/raslan/2016/paper03-Stromajerova_Baisa_Blahus.pdf}, year = {2016} }
TY - JOUR ID - 1362553 AU - Štromajerová, Adéla - Baisa, Vít - Blahuš, Marek PY - 2016 TI - Between Comparable and Parallel: English-Czech Corpus from Wikipedia PB - Tribun EU CY - Brno SN - 9788026310952 KW - parallel corpora KW - comparable corpora KW - Wikipedia UR - https://nlp.fi.muni.cz/raslan/2016/paper03-Stromajerova_Baisa_Blahus.pdf N2 - We describe the process of creating a parallel corpus from Czech and English Wikipedias using methods which are language independent. The corpus consists of Czech and English Wikipedia articles, the Czech ones being translations of the English ones, is aligned on sentence level and is accessible in Sketch Engine corpus manager. ER -
ŠTROMAJEROVÁ, Adéla, Vít BAISA and Marek BLAHUŠ. Between Comparable and Parallel: English-Czech Corpus from Wikipedia. In \textit{RASLAN 2016 Recent Advances in Slavonic Natural Language Processing}. Brno: Tribun EU, 2016, p.~3-8. ISBN~978-80-263-1095-2.
|