bert-uncased-keyword-extractor Open-source Keyword Extraction Model - Free for Keyword Extraction from English Texts

Bert Uncased Keyword Extractor

Developed by yanekyuk

A keyword extraction model fine-tuned based on bert-base-uncased, suitable for English text keyword extraction tasks

EnglishOpen Source License:Apache-2.0 #English Keyword Extraction #High-Precision BERT Fine-Tuning #Financial News Analysis

Downloads 10.80k

Release Time : 6/5/2022

Model Overview

This model is fine-tuned from bert-base-uncased and specifically designed for extracting key information from English texts. It performs excellently on the evaluation set, achieving an F1 score of 0.8684.

Model Features

High-Precision Keyword Extraction

Achieves a precision of 0.8547 and recall of 0.8825 on the evaluation set

BERT-Based Architecture

Utilizes BERT's powerful contextual understanding capabilities for keyword extraction

Optimized Training

Fine-tuned over 8 epochs with the loss value reduced to 0.1247

Model Capabilities

English text keyword extraction

Financial news key information extraction

Core content identification in tech reports

Use Cases

News Analysis

Key Data Extraction from Financial News

Extracts key information such as transaction amounts and company names from financial reports

Successfully extracted keywords like '$61 billion', 'Broadcom', and 'VMware' in the example

Tech News Event Identification

Identifies major events and participants in tech news

Correctly extracted keywords like 'Google', 'antitrust investigation', and 'UK' in the example

Business Intelligence

M&A Transaction Analysis

Extracts key details of mergers and acquisitions from business reports

Extracted transaction details like '$61 billion acquisition' and '$142.50 per share' in the example

🚀 bert-uncased-keyword-extractor

This model, bert-uncased-keyword-extractor, is a fine - tuned version of bert-base-uncased on an unknown dataset. It provides valuable capabilities for keyword extraction tasks and has achieved notable results on the evaluation set.

🚀 Quick Start

The model is ready to be used for keyword extraction tasks. You can integrate it into your projects based on the framework versions it supports.

✨ Features

Fine - Tuned: Based on the well - known bert-base-uncased model, fine - tuned for specific keyword extraction tasks.
Multiple Metrics: Evaluated using precision, recall, accuracy, and F1 score, indicating its effectiveness in keyword extraction.

📦 Installation

There is no specific installation information provided in the original document.

💻 Usage Examples

There are no code examples provided in the original document.

📚 Documentation

Model Evaluation Results

This model achieves the following results on the evaluation set:

Loss: 0.1247
Precision: 0.8547
Recall: 0.8825
Accuracy: 0.9741
F1: 0.8684

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

Property	Details
Learning Rate	2e - 05
Train Batch Size	16
Eval Batch Size	16
Seed	42
Optimizer	Adam with betas=(0.9, 0.999) and epsilon = 1e - 08
LR Scheduler Type	linear
Num Epochs	8
Mixed Precision Training	Native AMP

Training Results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	Accuracy	F1
0.165	1.0	1875	0.1202	0.7109	0.7766	0.9505	0.7423
0.1211	2.0	3750	0.1011	0.7801	0.8186	0.9621	0.7989
0.0847	3.0	5625	0.0945	0.8292	0.8044	0.9667	0.8166
0.0614	4.0	7500	0.0927	0.8409	0.8524	0.9711	0.8466
0.0442	5.0	9375	0.1057	0.8330	0.8738	0.9712	0.8529
0.0325	6.0	11250	0.1103	0.8585	0.8743	0.9738	0.8663
0.0253	7.0	13125	0.1204	0.8453	0.8825	0.9735	0.8635
0.0203	8.0	15000	0.1247	0.8547	0.8825	0.9741	0.8684

Framework Versions

Transformers 4.19.2
Pytorch 1.11.0+cu113
Datasets 2.2.2
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