ProHiryu / Bert Chinese Ner
Licence: mit
使用预训练语言模型BERT做中文NER
Stars: ✭ 758
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Bert Chinese Ner
Cluener2020
CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition
Stars: ✭ 689 (-9.1%)
Mutual labels: chinese, ner
Chinesener
中文命名实体识别,实体抽取,tensorflow,pytorch,BiLSTM+CRF
Stars: ✭ 938 (+23.75%)
Mutual labels: chinese, ner
Bert Ner Pytorch
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
Stars: ✭ 654 (-13.72%)
Mutual labels: chinese, ner
Uer Py
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
Stars: ✭ 1,295 (+70.84%)
Mutual labels: chinese, ner
Eda nlp for chinese
An implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。
Stars: ✭ 660 (-12.93%)
Mutual labels: chinese
Ngram2vec
Four word embedding models implemented in Python. Supporting arbitrary context features
Stars: ✭ 703 (-7.26%)
Mutual labels: chinese
Reactnativematerials
React Native的中文参考资料,包括开源库,文字/视频资料,相关工具等
Stars: ✭ 647 (-14.64%)
Mutual labels: chinese
Yedda
YEDDA: A Lightweight Collaborative Text Span Annotation Tool. Code for ACL 2018 Best Demo Paper Nomination.
Stars: ✭ 704 (-7.12%)
Mutual labels: ner
Rrpl
Describing Chinese Characters with Recursive Radical Packing Language (RRPL)
Stars: ✭ 649 (-14.38%)
Mutual labels: chinese
Rasa chatbot cn
building a chinese dialogue system based on the newest version of rasa(基于最新版本rasa搭建的对话系统)
Stars: ✭ 723 (-4.62%)
Mutual labels: chinese
Handright
A lightweight Python library for simulating Chinese handwriting
Stars: ✭ 634 (-16.36%)
Mutual labels: chinese
Opentracing Specification Zh
OpenTracing标准(中文版) `zh` (Chinese) translation of the opentracing/specification
Stars: ✭ 717 (-5.41%)
Mutual labels: chinese
bert-chinese-ner
前言
使用预训练语言模型BERT做中文NER尝试,fine - tune BERT模型
PS: 移步最新albert fine-tune ner模型
代码参考
使用方法
从BERT-TF下载bert源代码,存放在路径下bert文件夹中
从BERT-Base Chinese下载模型,存放在checkpoint文件夹下
使用BIO数据标注模式,使用人民日报经典数据
train:
python BERT_NER.py --data_dir=data/ --bert_config_file=checkpoint/bert_config.json --init_checkpoint=checkpoint/bert_model.ckpt --vocab_file=vocab.txt --output_dir=./output/result_dir/
结果
经过100个epoch跑出来的结果
eval_f = 0.9662649
eval_precision = 0.9668882
eval_recall = 0.9656949
global_step = 135181
loss = 40.160034
测试结果第一句:
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].