Tagger SentiOne - version 2
This is the second version of the morpho-syntactic tagger for the Polish language, adapted to UGC-processing. It has been enriched with some heuristics to improve its accuracy and a tokenizer.
Result filters
Metadata provider
- DSpace (4)
Language
- Polish (4)
Resource type
- Unspecified (4)
Tool task
- Lemmatisation (2)
- Tokenisation (2)
- Parsing (1)
- Tagging (1)
Availability
- Attribution (4)
- Share-alike (2)
Organisation
- Wojciech Jaworski (2)
- SentiOne (1)
- Wiktor Walentynowicz (1)
Project
Keywords
- MWE detection (2)
- lemmatization (2)
- sentence boundaries detection (2)
- tokenization (2)
- Polish (1)
- parsing (1)
- tagger (1)
Loading...
4 record(s) found
Search results
-
-
ENIAMtoolkit (2017-03-06)
ENIAMtoolkit is a collection of libraries that: - perform tokenization, lemmatization, part of speech tagging; - detect MWE and abbreviations; - split text into sentences; - LCG parsing. -
ENIAMtoolkit
ENIAMtoolkit is a collection of libraries that: - perform tokenization, lemmatization, part of speech tagging; - detect MWE and abbreviations; - split text into sentences. -
MorphoDiTa-based tagger for Polish language
MorphoDiTa-based tagger for Polish language. It is a tool for morphosyntactic unification for the Polish language, according to the NKJP tagset.