kmdn/combining-linking-techniques
Combining Linking Techniques (CLiT) is an entity linking combination and execution framework, allowing for the seamless integration of EL systems and result exploitation for the sake of system reusability, result reproducibility, analysis and continuous improvement. (We hate waste. Especially wasting time. So let's reuse instead!)
This tool helps researchers and data scientists working with text documents to quickly and efficiently identify and link entities (like people, places, or organizations) within their data. You input plain text, and it outputs annotated documents or hyperlinks to knowledge bases like Wikipedia, showing you exactly what entities were found and where. It's designed for anyone who needs to extract structured information from unstructured text and wants to compare or combine different entity linking approaches.
No commits in the last 6 months.
Use this if you need to extract and link entities from text, want to compare different entity linking systems, or custom-build a linking pipeline by mixing and matching components.
Not ideal if you're looking for a simple, out-of-the-box solution with no customization or if your primary need is not entity linking.
Stars
8
Forks
1
Language
Python
License
MIT
Category
Last pushed
Apr 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kmdn/combining-linking-techniques"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
amazon-science/ReFinED
ReFinED is an efficient and accurate entity linking (EL) system.
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.