Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{1195822, author = {Bojar, Ondřej and Diatka, Vojtěch and Rychlý, Pavel and Straňák, Pavel and Suchomel, Vít and Tamchyna, Aleš and Zeman, Daniel}, address = {Reykjavik, Iceland}, booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Hrafn Loftsson and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis}, keywords = {Machine Translation; SpeechToSpeech Translation; Metadata}, howpublished = {elektronická verze "online"}, language = {eng}, location = {Reykjavik, Iceland}, isbn = {978-2-9517408-8-4}, pages = {3550-3555}, publisher = {European Language Resources Association (ELRA)}, title = {HindEnCorp – Hindi-English and Hindi-only Corpus for Machine Translation}, url = {http://www.lrec-conf.org/proceedings/lrec2014/summaries/835.html}, year = {2014} }
TY - JOUR ID - 1195822 AU - Bojar, Ondřej - Diatka, Vojtěch - Rychlý, Pavel - Straňák, Pavel - Suchomel, Vít - Tamchyna, Aleš - Zeman, Daniel PY - 2014 TI - HindEnCorp – Hindi-English and Hindi-only Corpus for Machine Translation PB - European Language Resources Association (ELRA) CY - Reykjavik, Iceland SN - 9782951740884 KW - Machine Translation KW - SpeechToSpeech Translation KW - Metadata UR - http://www.lrec-conf.org/proceedings/lrec2014/summaries/835.html L2 - http://www.lrec-conf.org/proceedings/lrec2014/summaries/835.html N2 - We present HindEnCorp, a parallel corpus of Hindi and English, and HindMonoCorp, a monolingual corpus of Hindi in their release version 0.5. Both corpora were collected from web sources and preprocessed primarily for the training of statistical machine translation systems. HindEnCorp consists of 274k parallel sentences (3.9 million Hindi and 3.8 million English tokens). HindMonoCorp amounts to 787 million tokens in 44 million sentences. Both the corpora are freely available for non-commercial research and their preliminary release has been used by numerous participants of the WMT 2014 shared translation task. ER -
BOJAR, Ondřej, Vojtěch DIATKA, Pavel RYCHLÝ, Pavel STRAŇÁK, Vít SUCHOMEL, Aleš TAMCHYNA a Daniel ZEMAN. HindEnCorp – Hindi-English and Hindi-only Corpus for Machine Translation. Online. In Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Hrafn Loftsson and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis. \textit{Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)}. Reykjavik, Iceland: European Language Resources Association (ELRA), 2014, s.~3550-3555. ISBN~978-2-9517408-8-4.
|