philipperemy/stanford-openie-python
Stanford Open Information Extraction made simple!
This tool helps you automatically extract key facts from English text without needing to define what you're looking for in advance. You provide raw text documents, and it outputs structured subject-relation-object triples, like (Barack Obama; was born in; Hawaii). This is useful for researchers, analysts, or anyone who needs to quickly pull out specific relationships and entities from large volumes of unstructured text.
681 stars. No commits in the last 6 months.
Use this if you need to automatically identify and extract relationships and factual statements from a collection of English texts, such as articles, reports, or customer feedback, to gain insights or build a knowledge base.
Not ideal if you need to extract information in languages other than English or if you require a highly specific, pre-defined set of entities and relationships, which might be better handled by a custom named entity recognition (NER) or relation extraction model.
Stars
681
Forks
104
Language
Python
License
ISC
Category
Last pushed
Jan 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/philipperemy/stanford-openie-python"
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
uma-pi1/minie
An open information extraction system that provides compact extractions
xusenlinzy/FastIE
A training and inference framework for open ner and re models!...