| RYCHLÝ, Pavel. KernelTagger – a PoS Tagger for Very Small Amount of Training Data. In Aleš Horák, Pavel Rychlý, Adam Rambousek. Proceedings of the Eleventh Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2017. Brno: Tribun EU, 2017, s. 107-110. ISBN 978-80-263-1340-3. |
Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{1400973,
author = {Rychlý, Pavel},
address = {Brno},
booktitle = {Proceedings of the Eleventh Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2017},
editor = {Aleš Horák, Pavel Rychlý, Adam Rambousek},
keywords = {PoS tagging; morphological tagging; language model; Czech},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Brno},
isbn = {978-80-263-1340-3},
pages = {107-110},
publisher = {Tribun EU},
title = {KernelTagger – a PoS Tagger for Very Small Amount of Training Data},
url = {http://raslan2017.nlp-consulting.net/proceedings},
year = {2017}
}
TY - JOUR
ID - 1400973
AU - Rychlý, Pavel
PY - 2017
TI - KernelTagger – a PoS Tagger for Very Small Amount of Training Data
PB - Tribun EU
CY - Brno
SN - 9788026313403
KW - PoS tagging
KW - morphological tagging
KW - language model
KW - Czech
UR - http://raslan2017.nlp-consulting.net/proceedings
N2 - The paper describes a new Part of speech (PoS) tagger which can learn a PoS tagging language model from very short annotated text with the use of much bigger non-annotated text. Only several sentences could be used for training to achieve much better accuracy than a baseline. The results cannot be compared to the results of state-of-the-art taggers but it could be used during the annotation process for a pre-annotation.
ER -
RYCHLÝ, Pavel. KernelTagger – a PoS Tagger for Very Small Amount of Training Data. In Aleš Horák, Pavel Rychlý, Adam Rambousek. \textit{Proceedings of the Eleventh Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2017}. Brno: Tribun EU, 2017, s.~107-110. ISBN~978-80-263-1340-3.
|
