RiTUAL-MBZUAI/multimodal_NER

"Can images help recognize entities? A study of the role of images for Multimodal NER" (W-NUT at EMNLP 2021)

30
/ 100
Emerging

This is a research project exploring how images can improve the accuracy of named entity recognition (NER) in text, particularly from social media. It takes text data, associated images, and optionally image captions as input to identify and categorize specific entities like people, organizations, or locations. The primary users are researchers in natural language processing (NLP) and multimodal AI, specifically those studying information extraction from user-generated content.

No commits in the last 6 months.

Use this if you are an NLP researcher investigating how visual information can enhance named entity recognition performance on text, especially from noisy, user-generated sources.

Not ideal if you need a production-ready, off-the-shelf tool for immediate named entity recognition on your data without significant setup or research-oriented configuration.

Natural Language Processing Multimodal AI Research Information Extraction Social Media Analysis Academic Research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

21

Forks

2

Language

Python

License

MIT

Last pushed

Nov 14, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/RiTUAL-MBZUAI/multimodal_NER"

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