Determined22/zh-NER-TF
A character-based BiLSTM-CRF sequence labeling model for Chinese Named Entity Recognition recognizing PERSON, LOCATION, and ORGANIZATION entities.
Not currently ranked — collecting fresh signals.
star history
This repository provides a simple character-based BiLSTM-CRF model for Chinese NER. The model uses a lookup layer for character embeddings, a BiLSTM layer to capture bidirectional context, and a CRF layer to ensure valid tag sequences (preventing invalid transitions like I-LOC following B-PER). It labels each character with BIO tags for three entity types: PERSON, LOCATION, and ORGANIZATION.
Frequently asked
- What is Determined22/zh-NER-TF?
- A character-based BiLSTM-CRF sequence labeling model for Chinese Named Entity Recognition recognizing PERSON, LOCATION, and ORGANIZATION entities.
- Is zh-NER-TF open source?
- Yes — Determined22/zh-NER-TF is an open-source project tracked on heatdrop.
- What language is zh-NER-TF written in?
- Determined22/zh-NER-TF is primarily written in Python.
- How popular is zh-NER-TF?
- Determined22/zh-NER-TF has 2.3k stars on GitHub.
- Where can I find zh-NER-TF?
- Determined22/zh-NER-TF is on GitHub at https://github.com/Determined22/zh-NER-TF.