scibert_scivocab_uncased-finetuned-ner Open Source Model - Accurately Identify Drug Names and Adverse Reaction Entities

Scibert Scivocab Uncased Finetuned Ner

Developed by jsylee

A named entity recognition model fine-tuned based on SciBERT, specifically designed to identify drug names and adverse drug reaction entities

Sequence Labeling

Transformers

English#Drug Identification #Adverse Reaction Extraction #Medical NER

Downloads 10.70k

Release Time : 3/2/2022

Model Overview

This model can accurately identify drug names and adverse drug reaction entities from medical texts, suitable for drug safety monitoring and medical literature analysis.

Model Features

Specialized for Medical Domain

Optimized specifically for medical texts, capable of accurately identifying drug names and adverse drug reactions

SciBERT Foundation

Based on the SciBERT pre-trained model, with strong capabilities in understanding scientific texts

Five Entity Categories

Supports fine-grained recognition of drugs (B-DRUG/I-DRUG) and adverse reactions (B-EFFECT/I-EFFECT)

Model Capabilities

Medical text entity recognition

Drug name identification

Adverse drug reaction identification

Scientific literature analysis

Use Cases

Drug Safety Monitoring

Adverse Drug Reaction Report Analysis

Extract relationships between drugs and adverse reactions from medical reports or literature

Automatically identify drugs and their potential adverse reactions

Medical Literature Mining

Drug Side Effect Research

Extract drug side effect information from medical literature

Help researchers quickly obtain drug safety data

🚀 SciBERT-based Named Entity Recognition Model for Drugs and Adverse Effects

This is a SciBERT-based model fine-tuned to perform Named Entity Recognition for drug names and adverse drug effects. It can classify input tokens into different classes related to drugs and their adverse effects, offering valuable insights in the medical field.

model image

✨ Features

Named Entity Recognition: Specifically designed to identify drug names and adverse drug effects.
Five-Class Classification: Classifies input tokens into one of five classes:
- B-DRUG: beginning of a drug entity
- I-DRUG: within a drug entity
- B-EFFECT: beginning of an AE entity
- I-EFFECT: within an AE entity
- O: outside either of the above entities

🚀 Quick Start

To get started using this model for inference, simply set up an NER pipeline like below:

from transformers import (AutoModelForTokenClassification, 
                          AutoTokenizer, 
                          pipeline,
                          )

model_checkpoint = "jsylee/scibert_scivocab_uncased-finetuned-ner"
model = AutoModelForTokenClassification.from_pretrained(model_checkpoint, num_labels=5,
                                                        id2label={0: 'O', 1: 'B-DRUG', 2: 'I-DRUG', 3: 'B-EFFECT', 4: 'I-EFFECT'} 
                                                        )                                                        
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

model_pipeline = pipeline(task="ner", model=model, tokenizer=tokenizer)

print( model_pipeline ("Abortion, miscarriage or uterine hemorrhage associated with misoprostol (Cytotec), a labor-inducing drug."))

📚 Documentation

SciBERT: SciBERT on Hugging Face
Dataset: ADE Corpus V2 on Hugging Face

📦 Additional Information

Property	Details
Tags	Named Entity Recognition, SciBERT, Adverse Effect, Drug, Medical
Datasets	ade_corpus_v2
Widget Examples	Abortion, miscarriage or uterine hemorrhage associated with misoprostol (Cytotec), a labor-inducing drug. Addiction to many sedatives and analgesics, such as diazepam, morphine, etc. Birth defects associated with thalidomide Bleeding of the intestine associated with aspirin therapy Cardiovascular disease associated with COX-2 inhibitors (i.e. Vioxx)

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