Open-source model albert-large-v2-finetuned-abbDet - A great helper for named entity recognition in scientific literature

Albert Large V2 Finetuned Abbdet

Developed by surrey-nlp

This model is a Named Entity Recognition (NER) model fine-tuned on the PLOD-unfiltered dataset based on ALBERT-large-v2, excelling in the field of scientific literature.

Sequence Labeling

Transformers

EnglishOpen Source License:Apache-2.0 #Scientific Literature NER #High-precision Entity Recognition #Biomedical Text

Downloads 16

Release Time : 4/22/2022

Model Overview

A named entity recognition model optimized for scientific literature, capable of accurately identifying professional terms and entities in texts.

Model Features

High-precision Recognition

Achieves 96.55% precision and 96.08% recall on the PLOD-unfiltered dataset

Scientific Literature Optimization

Specifically optimized for professional terms and entities in scientific literature

Efficient Training

Based on the ALBERT architecture, reducing parameter size while maintaining high performance

Model Capabilities

Scientific Term Recognition

Named Entity Recognition

Text Token Classification

Use Cases

Academic Research

Scientific Literature Analysis

Automatically identify key terms and entities in research papers

Improves literature processing efficiency and supports knowledge graph construction

Academic Knowledge Extraction

Extract professional terms and concepts from research papers

Supports academic database construction and knowledge discovery

Information Processing

Professional Document Processing

Process technical documents containing professional terms

Enhances automated document processing efficiency

🚀 albert-large-v2-finetuned-ner_with_callbacks

This model is a fine - tuned version of albert-large-v2 on the PLOD-unfiltered dataset. It can be used for token - classification tasks and has achieved high performance in precision, recall, F1 score, and accuracy on the evaluation set.

🚀 Quick Start

This model is ready for use in token - classification tasks. You can load it through the Hugging Face Transformers library and start making predictions.

✨ Features

Fine - tuned: Based on the albert-large-v2 model, fine - tuned on the PLOD-unfiltered dataset.
High Performance: Achieved excellent results in precision, recall, F1 score, and accuracy on the evaluation set.

📦 Installation

No specific installation steps are provided in the original document.

📚 Documentation

Model Information

Property	Details
Model Type	albert-large-v2-finetuned-ner_with_callbacks
Base Model	albert-large-v2
Training Data	surrey-nlp/PLOD-unfiltered
Metrics	precision, recall, f1, accuracy

Evaluation Results

This model achieves the following results on the evaluation set:

Loss: 0.1235
Precision: 0.9655
Recall: 0.9608
F1: 0.9632
Accuracy: 0.9589

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e - 05
train_batch_size: 8
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
num_epochs: 6

Training Results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1377	0.49	7000	0.1294	0.9563	0.9422	0.9492	0.9436
0.1244	0.98	14000	0.1165	0.9589	0.9504	0.9546	0.9499
0.107	1.48	21000	0.1140	0.9603	0.9509	0.9556	0.9511
0.1088	1.97	28000	0.1086	0.9613	0.9551	0.9582	0.9536
0.0918	2.46	35000	0.1059	0.9617	0.9582	0.9600	0.9556
0.0847	2.95	42000	0.1067	0.9620	0.9586	0.9603	0.9559
0.0734	3.44	49000	0.1188	0.9646	0.9588	0.9617	0.9574
0.0725	3.93	56000	0.1065	0.9660	0.9599	0.9630	0.9588
0.0547	4.43	63000	0.1273	0.9662	0.9602	0.9632	0.9590
0.0542	4.92	70000	0.1235	0.9655	0.9608	0.9632	0.9589
0.0374	5.41	77000	0.1401	0.9647	0.9613	0.9630	0.9586
0.0417	5.9	84000	0.1380	0.9641	0.9622	0.9632	0.9588

Framework Versions

Transformers 4.18.0
Pytorch 1.10.1+cu111
Datasets 2.1.0
Tokenizers 0.12.1

📄 License

This model is licensed under the Apache - 2.0 license.

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