HITsz-TMG/GEMEL

Official implementation of our LREC-COLING 2024 paper "Generative Multimodal Entity Linking".

26
/ 100
Experimental

This project helps identify and link entities mentioned in text and images (like a person's name or a product) to their correct entries in a knowledge base. You input text and corresponding images, and it outputs the precise name of the entity. Anyone working with content that combines text and visuals, such as researchers, data scientists, or content managers, would find this useful.

No commits in the last 6 months.

Use this if you need to accurately identify and link entities from documents or web pages that contain both text and images to a structured knowledge base, especially for less common entities.

Not ideal if your primary need is for purely text-based entity linking or if you require a solution that doesn't involve large language models.

information-extraction knowledge-graph-construction multimodal-data-analysis content-understanding named-entity-recognition
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

36

Forks

4

Language

Python

License

Last pushed

Feb 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/HITsz-TMG/GEMEL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.