Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{1073390, author = {Dovudov, Gulshan and Suchomel, Vít and Šmerk, Pavel}, address = {Istanbul}, booktitle = {Proceedings of the Workshop on Language Technology for Normalisation of Less-Resourced Languages (SALTMIL 8/AfLaT 2012)}, keywords = {Tajik language; Tajik corpus; morphological analysis of Tajik}, howpublished = {elektronická verze "online"}, language = {eng}, location = {Istanbul}, isbn = {978-2-9517408-7-7}, pages = {93-98}, publisher = {European Language Resources Association (ELRA)}, title = {POS Annotated 50M Corpus of Tajik Language}, url = {http://www.cnts.ua.ac.be/sites/default/files/saltmil8-aflat2012.pdf}, year = {2012} }
TY - JOUR ID - 1073390 AU - Dovudov, Gulshan - Suchomel, Vít - Šmerk, Pavel PY - 2012 TI - POS Annotated 50M Corpus of Tajik Language PB - European Language Resources Association (ELRA) CY - Istanbul SN - 9782951740877 KW - Tajik language KW - Tajik corpus KW - morphological analysis of Tajik UR - http://www.cnts.ua.ac.be/sites/default/files/saltmil8-aflat2012.pdf L2 - http://www.cnts.ua.ac.be/sites/default/files/saltmil8-aflat2012.pdf N2 - Paper presents by far the largest available computer corpus of Tajik language of the size of more than 50 million words. To obtain the texts for the corpus two different approaches were used and the paper offers a description of both of them. Then the paper describes a newly developed morphological analyzer of Tajik and presents some statistics of its application on the corpus. ER -
DOVUDOV, Gulshan, Vít SUCHOMEL a Pavel ŠMERK. POS Annotated 50M Corpus of Tajik Language. Online. In \textit{Proceedings of the Workshop on Language Technology for Normalisation of Less-Resourced Languages (SALTMIL 8/AfLaT 2012)}. Istanbul: European Language Resources Association (ELRA), 2012, s.~93-98. ISBN~978-2-9517408-7-7.
|