dc.contributor.author |
Marcińczuk, Michał |
dc.date.accessioned |
2018-09-07T09:44:42Z |
dc.date.available |
2018-09-07T09:44:42Z |
dc.date.issued |
2018-09-07 |
dc.identifier.uri |
http://hdl.handle.net/11321/598 |
dc.description |
Liner2.6 NER NKJP model
The package contains a pre-trained Liner2 (https://github.com/CLARIN-PL/Liner2) model for recognition named entities according to NKJP guidelines. The model was trained on the NKJP corpus (http://nkjp.pl/) and evaluated in the PolEval 2018 Task 2 (http://poleval.pl/tasks/).
The model won third place with the following results: Exact — 0.778, Overlap — 0.818, Final — 0.810.
References:
* NKJP corpus in TEI format — http://clip.ipipan.waw.pl/NationalCorpusOfPolish?action=AttachFile&do=view&target=NKJP-PodkorpusMilionowy-1.2.tar.gz
* PolEval 2018 Task 2 evaluation corpus — http://mozart.ipipan.waw.pl/~axw/poleval2018/ |
dc.language.iso |
pol |
dc.publisher |
Wrocław University of Science and Technology |
dc.rights |
GNU GPL3 |
dc.rights.uri |
http://www.gnu.org/licenses/gpl-3.0.en.html |
dc.rights.label |
PUB |
dc.source.uri |
https://github.com/CLARIN-PL/Liner2 |
dc.subject |
NER |
dc.subject |
Liner2 |
dc.subject |
information extraction |
dc.subject |
named entities |
dc.title |
Liner2.6 model NER NKJP |
dc.type |
toolService |
metashare.ResourceInfo#ContentInfo.detailedType |
other |
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent |
true |
hidden |
false |
hasMetadata |
false |
has.files |
yes |
branding |
CLARIN-PL |
demo.uri |
http://ws.clarin-pl.eu/ner.shtml |
contact.person |
Michał Marcińczuk marcinczuk@gmail.com Wrocław University of Science and Technology |
sponsor |
Ministry of Science and Higher Education (Poland) 6358/IA/119/2013 CLARIN-PL nationalFunds |
files.size |
135532160 |
files.count |
2 |