HWTCMNER Open-Source Named Entity Recognition Model - Specifically Designed for the Traditional Chinese Medicine Field with Leading NER Performance

Hwtcmner

Developed by Monor

A BERT-fine-tuned named entity recognition model specifically designed for the TCM field, achieving leading performance in NER tasks within this domain.

Sequence Labeling

Transformers

ChineseOpen Source License:Apache-2.0 #TCM NER #Prescription Recognition #Ancient Text Analysis

Downloads 18

Release Time : 6/7/2024

Model Overview

TCMNER is a BERT-fine-tuned named entity recognition model specifically designed for the TCM field, capable of identifying six types of entities: prescriptions, herbs, sources, disease names, symptoms, and syndromes.

Model Features

Specialized for TCM Field

Specifically designed for the TCM field, achieving leading performance in NER tasks within this domain.

Six-category Entity Recognition

Capable of identifying six types of entities: prescriptions, herbs, sources, disease names, symptoms, and syndromes.

Optimized Based on RoBERTa

TCMRoBERTa, a TCM-specific model optimized based on the RoBERTa architecture.

Model Capabilities

Named entity recognition in TCM texts

Prescription recognition

Herb recognition

Source recognition

Disease name recognition

Symptom recognition

Syndrome recognition

Use Cases

TCM Text Processing

TCM Literature Analysis

Used to analyze key entities in TCM literature, such as prescriptions and herbs.

Accurately identifies six types of entities in the literature.

TCM Knowledge Graph Construction

Used to construct TCM knowledge graphs by extracting key entity information.

Provides high-quality entity recognition results to support knowledge graph construction.

🚀 TCMNER

TCMNER is a fine - tuned BERT model designed for Named Entity Recognition in Traditional Chinese Medicine, delivering state - of - the - art performance in the NER task.

About Author.
Our Products

🚀 Quick Start

You can use this model with Transformers pipeline for NER.

Basic Usage

# Use this model with Transformers pipeline for NER.
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline

tokenizer = AutoTokenizer.from_pretrained("Monor/TCMNER")
model = AutoModelForTokenClassification.from_pretrained("Monor/TCMNER")

nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "化滞汤,出处：《证治汇补》卷八。。组成：青皮20g，陈皮20g，厚朴20g，枳实20g，黄芩20g，黄连20g，当归20g，芍药20g，木香5g，槟榔8g，滑石3g，甘草4g。。主治：下痢因于食积气滞者。"

ner_results = nlp(example)
print(ner_results)

✨ Features

TCMNER is a fine - tuned BERT model that is ready to use for Named Entity Recognition of Traditional Chinese Medicine and achieves state - of - the - art performance for the NER task. It has been trained to recognize six types of entities: prescription (方剂), herb (本草), source (来源), disease (病名), symptom (症状) and syndrome（证型）.

Specifically, this model is a TCMRoBERTa model, a fine - tuned model of RoBERTa for Traditional Chinese medicine, that was fine - tuned on the Chinese version of the Haiwei AI Lab's Named Entity Recognition dataset.

Currently, TCMRoBERTa is just a closed - source model for my own company and will be open - source in the future.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

📚 Documentation

Model Information

Property	Details
Model Type	TCMRoBERTa, a fine - tuned model of RoBERTa for Traditional Chinese medicine
Training Data	This model was fine - tuned on MY DATASET.

Label Explanation

Abbreviation	Description
O	Outside of a named entity
B - 方剂	Beginning of a prescription entity right after another prescription entity
I - 方剂	Prescription entity
B - 本草	Beginning of a herb entity right after another herb entity
I - 本草	Herb entity
B - 来源	Beginning of a source of prescription right after another source of prescription
I - 来源	Source entity
B - 病名	Beginning of a disease's name right after another disease's name
I - 病名	Disease's name
B - 症状	Beginning of a symptom right after another symptom
I - 症状	Symptom
B - 证型	Beginning of a syndrome right after another syndrome
I - 证型	Syndrome

Eval Results

alt text

📄 License

The model is under the Apache - 2.0 license.

⚠️ Important Note

The model is commercially available for free.
I am not going to write a paper about this model, if you use any details in your paper, please mention it, thanks.

💡 Usage Tip

All of our TCM domain models will be open - sourced soon, including:

A series of pre - trained models
Named entity recognition for TCM
Text localization in ancient images
OCR for ancient images

And so on

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご