Zobrazit minimální záznam
dc.contributor.author |
Papageorgiou, Haris |
dc.contributor.author |
Prokopidis, Prokopis |
dc.contributor.other |
Prokopidis, Prokopis |
dc.date.accessioned |
2014-07-30T21:34:28Z |
dc.date.available |
2014-07-30T21:34:28Z |
dc.date.issued |
2014-07-30 |
dc.identifier.uri |
http://hdl.handle.net/11372/LRT-1308 |
dc.description |
ILSP FBT Tagger is an adaptation of the Brill tagger trained on Greek text. It uses a PAROLE compatible tagset of 584 different tags which capture the morphosyntactic particularities of the Greek language. Working on the output of a sentence detection and tokenisation tool, the tagger assigns initial tags, looking up in a lexicon created from a manually annotated corpus during training. A suffix lexicon is used for initially tagging unknown words. 799 contextual rules are then applied to improve the initial phase output. |
dc.publisher |
ILSP/R.C. "Athena" |
dc.subject |
POS tagger |
dc.title |
ILSP Feature-based multi-tiered POS Tagger |
dc.type |
toolService |
has.files |
no |
additional.metadata |
Documentation language(s) (field_tool_documentation_langua):Greek
Language(s) of input data (field_tool_input_language):Greek
Implementation language(s) (field_tool_implementation_langu):Perl
Software requirements (field_tool_software_requirement):Perl
Short name (field_tool_short_name):ILSP FBT Tagger
Readily Available (field_tool_available):No
Nid:1166
Platform(s) (field_tool_platform):System independent
Character encoding of output data (field_tool_char_encoding_output):Unicode (UTF-8)||Greek (ISO 8859-7)
Approach (field_tool_aproach):Transformation-based error-driven learning
Open source code (field_tool_open_source_code):no
Language(s) of output data (field_tool_output_language):Greek
Character encoding of input data (field_tool_char_encoding):Unicode (UTF-8)||Greek (ISO 8859-7)
Relevant project(s) (field_tool_relevant_project):FBT Tagger is the result of an internal project at the Natural Language and Knowledge Extraction Department of ILSP/R.C. "Athena"
Version (field_tool_version):1.0 |
branding |
LRT + Open Submissions |
dc.coverage.placeName |
Greece |
files.size |
0 |
files.count |
0 |
Zobrazit minimální záznam