Title |
The JOS Morphosyntactically Tagged Corpus of Slovene |
Authors |
Tomaš Erjavec and Simon Krek |
Abstract |
The JOSmorphosyntactic resources for Slovene consist of the specifications, lexicon, and two corpora: jos100k, a 100,000 word balanced monolingual sampled corpus annotated with hand validated morphosyntactic descriptions (MSDs) and lemmas, and jos1M, the 1 million-word partially hand validated corpus. The two corpora have been sampled from the 600M-word Slovene reference corpus FidaPLUS. The JOS resources have a standardised encoding, with the MULTEXT-East-type morphosyntactic specifications and the corpora encoded according to the Text Encoding Initiative Guidelines P5. JOS resources are available as a dataset for research under the Creative Commons licence and are meant to facilitate developments of HLT for Slovene. |
Language |
Single language |
Topics |
Corpus (creation, annotation, etc.), Tagging, Standards for LRs |
Full paper |
The JOS Morphosyntactically Tagged Corpus of Slovene |
Slides |
- |
Bibtex |
@InProceedings{ERJAVEC08.89,
author = {Tomaš Erjavec and Simon Krek},
title = {The JOS Morphosyntactically Tagged Corpus of Slovene},
booktitle = {Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)},
year = {2008},
month = {may},
date = {28-30},
address = {Marrakech, Morocco},
editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Daniel Tapias},
publisher = {European Language Resources Association (ELRA)},
isbn = {2-9517408-4-0},
note = {http://www.lrec-conf.org/proceedings/lrec2008/},
language = {english}
} |