Bert4ner Base Chinese

🚀 BERT for Chinese Named Entity Recognition(bert4ner) Model

This is a Chinese named entity recognition model. The bert4ner-base-chinese model evaluates the PEOPLE (Renmin Ribao) test data.

The overall performance of BERT on the PEOPLE test:

It reaches a level close to SOTA on the PEOPLE test set.

The network structure of BertSoftmax (native BERT):

🚀 Quick Start

✨ Features

• This model can perform Chinese named entity recognition tasks.
• It achieves a high performance on the PEOPLE test set, approaching the SOTA level.

📦 Installation

This project is open - sourced in the named entity recognition project: nerpy, which supports the bert4ner model. You can call it through the following commands:

>>> from nerpy import NERModel
>>> model = NERModel("bert", "shibing624/bert4ner-base-chinese")
>>> predictions, raw_outputs, entities = model.predict(["常建良，男，1963年出生，工科学士，高级工程师"], split_on_space=False)
entities: [('常建良', 'PER'), ('1963年', 'TIME')]

The model files are composed as follows:

bert4ner-base-chinese
    ├── config.json
    ├── model_args.json
    ├── pytorch_model.bin
    ├── special_tokens_map.json
    ├── tokenizer_config.json
    └── vocab.txt

💻 Usage Examples

Basic Usage

Without nerpy, you can use the model like this:

First, you pass your input through the transformer model, then you have to apply the bio tag to get the entity words.

Install package:

pip install transformers seqeval

import os
import torch
from transformers import AutoTokenizer, AutoModelForTokenClassification
from seqeval.metrics.sequence_labeling import get_entities

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("shibing624/bert4ner-base-chinese")
model = AutoModelForTokenClassification.from_pretrained("shibing624/bert4ner-base-chinese")
label_list = ['I-ORG', 'B-LOC', 'O', 'B-ORG', 'I-LOC', 'I-PER', 'B-TIME', 'I-TIME', 'B-PER']

sentence = "王宏伟来自北京，是个警察，喜欢去王府井游玩儿。"


def get_entity(sentence):
    tokens = tokenizer.tokenize(sentence)
    inputs = tokenizer.encode(sentence, return_tensors="pt")
    with torch.no_grad():
        outputs = model(inputs).logits
    predictions = torch.argmax(outputs, dim=2)
    char_tags = [(token, label_list[prediction]) for token, prediction in zip(tokens, predictions[0].numpy())][1:-1]
    print(sentence)
    print(char_tags)

    pred_labels = [i[1] for i in char_tags]
    entities = []
    line_entities = get_entities(pred_labels)
    for i in line_entities:
        word = sentence[i[1]: i[2] + 1]
        entity_type = i[0]
        entities.append((word, entity_type))

    print("Sentence entity:")
    print(entities)


get_entity(sentence)

Output:

王宏伟来自北京，是个警察，喜欢去王府井游玩儿。
[('王', 'B-PER'), ('宏', 'I-PER'), ('伟', 'I-PER'), ('来', 'O'), ('自', 'O'), ('北', 'B-LOC'), ('京', 'I-LOC'), ('，', 'O'), ('是', 'O'), ('个', 'O'), ('警', 'O'), ('察', 'O'), ('，', 'O'), ('喜', 'O'), ('欢', 'O'), ('去', 'O'), ('王', 'B-LOC'), ('府', 'I-LOC'), ('井', 'I-LOC'), ('游', 'O'), ('玩', 'O'), ('儿', 'O'), ('。', 'O')]
Sentence entity:
[('王宏伟', 'PER'), ('北京', 'LOC'), ('王府井', 'LOC')]

📚 Documentation

Training Datasets

Chinese Named Entity Recognition Datasets

The data format of the CNER Chinese named entity recognition dataset:

美	B-LOC
国	I-LOC
的	O
华	B-PER
莱	I-PER
士	I-PER

我	O
跟	O
他	O

If you need to train bert4ner, please refer to https://github.com/shibing624/nerpy/tree/main/examples

📄 License

This project is under the Apache - 2.0 license.

📚 Citation

@software{nerpy,
  author = {Xu Ming},
  title = {nerpy: Named Entity Recognition toolkit},
  year = {2022},
  url = {https://github.com/shibing624/nerpy},
}