GU-DataLab/stance-detection-KE-MLM

Official resource of the paper "Knowledge Enhanced Masked Language Model for Stance Detection", NAACL 2021

29
/ 100
Experimental

Integrates knowledge-enhanced masked language modeling with BERT for fine-grained stance classification on political Twitter data, distinguishing between support, opposition, and neutral positions. Pre-trained models optimized for 2020 US election discourse are available on Hugging Face and leverage domain-specific MLM pre-training on 5M+ tweets alongside external knowledge injection. Includes manually annotated benchmark datasets (2,500 labeled tweets per candidate) and demonstrates performance gains over baseline BERT on downstream stance detection tasks.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

39

Forks

2

Language

Python

License

GPL-3.0

Last pushed

Oct 26, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/GU-DataLab/stance-detection-KE-MLM"

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