ppke-nlpg/purepos
PurePos is an open source hybrid morphological tagger.
This tool helps linguistics researchers and natural language processing practitioners automatically identify the grammatical role (part-of-speech) and base form (lemma) of words in text. You provide text where each word has its lemma and tag, and it outputs a model. You can then feed new, raw text into the model to get the same detailed annotations. It's especially useful for languages with complex grammar or when you have limited training examples.
No commits in the last 6 months.
Use this if you need to accurately identify parts of speech and lemmas in large volumes of text, especially for languages with rich morphology, and want to incorporate custom linguistic rules.
Not ideal if you're looking for a simple, off-the-shelf solution for common languages with ample existing NLP models and don't require deep morphological analysis or custom rule integration.
Stars
16
Forks
8
Language
Java
License
LGPL-3.0
Category
Last pushed
Oct 13, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ppke-nlpg/purepos"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dnanhkhoa/python-vncorenlp
A Python wrapper for VnCoreNLP using a bidirectional communication channel.
datquocnguyen/RDRPOSTagger
A fast and accurate POS and morphological tagging toolkit (EACL 2014)
OpenSextant/SolrTextTagger
A text tagger based on Lucene / Solr, using FST technology
ankane/informers
Fast transformer inference for Ruby
bentrevett/pytorch-pos-tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.