Jacen789/relation-extraction
BERT-powered Chinese relation extraction model classifying person-to-person relationships into 12 categories.
Not currently ranked — collecting fresh signals.
star history
This project implements a Chinese relation extraction system using a BERT-based neural network trained with PyTorch. The model classifies pairs of entities in Chinese text into relationship categories such as parent, spouse, teacher-student, siblings, and colleagues. It achieves 78% accuracy on a test set of 1000 samples after 20 training epochs.
Frequently asked
- What is Jacen789/relation-extraction?
- BERT-powered Chinese relation extraction model classifying person-to-person relationships into 12 categories.
- Is relation-extraction open source?
- Yes — Jacen789/relation-extraction is open source, released under the MIT license.
- What language is relation-extraction written in?
- Jacen789/relation-extraction is primarily written in Python.
- How popular is relation-extraction?
- Jacen789/relation-extraction has 468 stars on GitHub.
- Where can I find relation-extraction?
- Jacen789/relation-extraction is on GitHub at https://github.com/Jacen789/relation-extraction.