Determined22/zh-NER-TF
A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow)
Implements character-level sequence labeling with a CRF output layer that enforces valid tag transitions (e.g., preventing I-LOC after B-PER), addressing limitations of softmax-only approaches. Trained on the MSRA corpus to recognize PERSON, LOCATION, and ORGANIZATION entities, with BiLSTM layers capturing bidirectional context across Chinese character sequences. Built for TensorFlow 1.2 with support for custom datasets in BIO tag format and includes evaluation tools against the SIGHAN benchmark.
2,336 stars. No commits in the last 6 months.
Stars
2,336
Forks
928
Language
Python
License
—
Category
Last pushed
Apr 18, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Determined22/zh-NER-TF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hellohaptik/chatbot_ner
chatbot_ner: Named Entity Recognition for chatbots.
Rostlab/nalaf
NLP framework in python for entity recognition and relationship extraction
modelscope/AdaSeq
AdaSeq: An All-in-One Library for Developing State-of-the-Art Sequence Understanding Models
openeventdata/mordecai
Full text geoparsing as a Python library
NorskRegnesentral/skweak
skweak: A software toolkit for weak supervision applied to NLP tasks