amazon-science/ReFinED
ReFinED is an efficient and accurate entity linking (EL) system.
This tool helps researchers, data analysts, or content strategists automatically identify and categorize key entities within large volumes of text. You input raw text, and it outputs recognized entities like people, organizations, or locations, along with precise links to their corresponding Wikipedia or Wikidata entries. It's designed for anyone needing to accurately extract structured information from unstructured text data.
235 stars. No commits in the last 6 months.
Use this if you need to precisely identify specific real-world entities mentioned in text and link them to comprehensive knowledge bases like Wikipedia or Wikidata, especially for large datasets.
Not ideal if you only need general entity categories like 'PERSON' or 'LOCATION' and don't require specific links to knowledge base entries for each entity.
Stars
235
Forks
52
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/amazon-science/ReFinED"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
MartinoMensio/spacy-dbpedia-spotlight
A spaCy wrapper for DBpedia Spotlight
SDM-TIB/falcon2.0
Falcon 2.0 is a joint entity and relation linking tool over Wikidata.
Lucaterre/spacyfishing
A spaCy wrapper of Entity-Fishing (component) for named entity disambiguation and linking on Wikidata
dbpedia-spotlight/dbpedia-spotlight
DBpedia Spotlight is a tool for automatically annotating mentions of DBpedia resources in text.
lyutyuh/ASP
PyTorch implementation and pre-trained models for ASP - Autoregressive Structured Prediction...