Zobrazit minimální záznam
| dc.contributor.author |
Jongejan, Bart |
| dc.contributor.other |
Jongejan, Bart |
| dc.date.accessioned |
2014-07-30T21:33:49Z |
| dc.date.available |
2014-07-30T21:33:49Z |
| dc.date.issued |
2014-07-30 |
| dc.identifier.uri |
http://hdl.handle.net/11372/LRT-1249 |
| dc.description |
1) Fully automatic rule based lemmatization of inflected languages
2) Fully automatic training of lemmatization rules based on full form-lemma list |
| dc.publisher |
Københavns Universitet, Center for Sprogteknologi (CST) |
| dc.source.uri |
http://cst.dk/download/uk/ |
| dc.title |
CST's lemmatizer |
| dc.type |
toolService |
| has.files |
no |
| additional.metadata |
Language(s) of input data (field_tool_input_language):Danish||Dutch||English||German||Greek||Icelandic||Norwegian||Russian||Slovenian||Swedish
Implementation language(s) (field_tool_implementation_langu):C++
Software requirements (field_tool_software_requirement):None
Short name (field_tool_short_name):CSTlemma
Readily Available (field_tool_available):Readily available
Webservice link (field_tool_webservice_link):http://mail.cst.dk/tools/
Availibility (field_tool_availibility):Linguistic resources (data for training or trained rules) are not part of the downloadable program.
Nid:1023
System requirements (field_tool_system_requirements):Ample memory for training (GB-ish)
Platform(s) (field_tool_platform):Windows, *n*x
Character encoding of output data (field_tool_char_encoding_output):Greek (ISO 8859-7)||Latin 1 (ISO 8859-1)||Latin 2 (ISO 8859-2)||Turkish (ISO 8859-9)
Approach (field_tool_aproach):decision tree, handles suffixes
Open source code (field_tool_open_source_code):yes
Language(s) of output data (field_tool_output_language):Danish||Dutch||English||German||Greek||Icelandic||Norwegian||Russian||Slovenian||Swedish
Character encoding of input data (field_tool_char_encoding):Greek (ISO 8859-7)||Latin 1 (ISO 8859-1)||Latin 2 (ISO 8859-2)||Turkish (ISO 8859-9)
Relevant project(s) (field_tool_relevant_project):STO
Version (field_tool_version):2.13 |
| branding |
LRT + Open Submissions |
| dc.coverage.placeName |
Denmark |
| files.size |
0 |
| files.count |
0 |
Zobrazit minimální záznam
