RiTUAL-MBZUAI/multimodal_NER
"Can images help recognize entities? A study of the role of images for Multimodal NER" (W-NUT at EMNLP 2021)
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.
Stars
21
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
MantisAI/nervaluate
Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13
dice-group/gerbil
GERBIL - General Entity annotatoR Benchmark
bltlab/seqscore
SeqScore: Scoring for named entity recognition and other sequence labeling tasks
syuoni/eznlp
Easy Natural Language Processing
LHNCBC/metamaplite
A near real-time named-entity recognizer