tomasonjo/trinity-ie
Information extraction pipeline containing coreference resolution, named entity linking, and relationship extraction
This helps data analysts and researchers automatically turn unstructured text documents into structured data. It takes raw text, like articles or reports, and identifies key entities (people, places, organizations), resolves mentions of the same entity, and extracts the relationships between them. The output is a clear, interconnected view of information, making large volumes of text data much easier to analyze.
No commits in the last 6 months.
Use this if you need to systematically extract facts and relationships from large collections of text documents, moving beyond simple keyword searches to understand the 'who, what, and how' within your data.
Not ideal if you only need to perform basic text searches or if your primary goal is to categorize documents into predefined topics.
Stars
81
Forks
17
Language
Python
License
—
Category
Last pushed
Feb 12, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/tomasonjo/trinity-ie"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zjunlp/OpenUE
[EMNLP 2020] OpenUE: An Open Toolkit of Universal Extraction from Text
OpenSextant/Xponents
Geographic Place, Date/time, and Pattern entity extraction toolkit along with text extraction...
BaptisteBlouin/EventExtractionPapers
A list of NLP resources focused on event extraction task
philipperemy/stanford-openie-python
Stanford Open Information Extraction made simple!
uma-pi1/minie
An open information extraction system that provides compact extractions