turbopape/postagga
A Library to parse natural language in pure Clojure and ClojureScript
This tool helps you automatically extract specific pieces of information from natural language text, like a sentence or a paragraph. You provide examples of text that have already been broken down into parts of speech (like nouns, verbs, adjectives), and you define rules for how to pull out the data you need. The output is structured data that your applications can easily understand and act upon, useful for anyone building intelligent bots or systems that need to interpret user input.
163 stars. No commits in the last 6 months.
Use this if you need to transform unstructured text into structured data by teaching a system to recognize specific patterns and information within sentences.
Not ideal if you're looking for a pre-trained, off-the-shelf solution for common natural language processing tasks without any custom training or rule definition.
Stars
163
Forks
16
Language
Clojure
License
MIT
Category
Last pushed
Dec 15, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/turbopape/postagga"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apache/opennlp
Apache OpenNLP
stanfordnlp/CoreNLP
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing,...
dkpro/dkpro-core
Collection of software components for natural language processing (NLP) based on the Apache UIMA...
stanfordnlp/python-stanford-corenlp
Python interface to CoreNLP using a bidirectional server-client interface.
apache/opennlp-sandbox
Apache OpenNLP Sandbox