KER - Keyword Extractor

 
LINDAT / CLARIAH-CZ
  Authors
Libovický, Jindřich
  Item identifier
http://hdl.handle.net/11234/1-1650
 Demo URL
https://lindat.mff.cuni.cz/services/ker
 Date issued
2016-02-22
 Type
toolService
 Language(s)
Czech , English
 Description
KER is a keyword extractor that was designed for scanned texts in Czech and English. It is based on the standard tf-idf algorithm with the idf tables trained on texts from Wikipedia. To deal with the data sparsity, texts are preprocessed by Morphodita: morphological dictionary and tagger.
 Publisher
Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
 Subject(s)
keyword extraction
 Collection(s)
LINDAT / CLARIAH-CZ Data & Tools
Show full item record
 

 Files in this item

 Download all files in item (25.99 MB)
This item is
Publicly Available
and licensed under:
Apache License 2.0
Icon
Name
ker-1.0.0.tar.gz
Size
10.51 KB
Format
application/x-gzip
Description
Archive with the release sources
MD5
113db6ff955a1c5cb43f33ac7e3d62bf
 Download file  Preview
 File Preview  
  • ker-1.0.0
    • README.md49 B
    • .gitignore67 B
    • .gitmodules0 B
    • prepare_venv.sh137 B
    • prepare_idf_table.py2 kB
    • keywords.py5 kB
    • server.py8 kB
    • LICENSE7 kB
    • web.html8 kB
    • pax_global_header52 B
Icon
Name
cs_idf_table.pickle
Size
22.16 MB
Format
Unknown
Description
IDF model for Czech
MD5
07ada26258f3f5be28ef82b41c7324e0
 Download file
Icon
Name
en_idf_table.pickle
Size
3.82 MB
Format
Unknown
Description
IDF model for English
MD5
cfd4ba647032a22c35d1fda736046e00
 Download file