illiterate/BertClassifier
基于PyTorch的BERT中文文本分类模型（BERT Chinese text classification model implemented by PyTorch）
Leverages Hugging Face's transformers library to extract sentence embeddings from pretrained BERT, feeding the [CLS] token representation through a linear classification layer and softmax for 10-category Chinese news classification. Achieves 0.92 accuracy on the THUCNews dataset (50k training samples across sports, entertainment, real estate, education, and other domains). Designed as an educational implementation with straightforward architecture suitable for NLP beginners to understand BERT fine-tuning fundamentals.
203 stars. No commits in the last 6 months.
Stars
203
Forks
25
Language
Python
License
MIT
Category
Last pushed
Mar 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/illiterate/BertClassifier"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lonePatient/Bert-Multi-Label-Text-Classification
This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text...
mim-solutions/bert_for_longer_texts
BERT classification model for processing texts longer than 512 tokens. Text is first divided...
OctoberChang/X-Transformer
X-Transformer: Taming Pretrained Transformers for eXtreme Multi-label Text Classification
QData/LaMP
ECML 2019: Graph Neural Networks for Multi-Label Classification
GT4SD/zero-shot-bert-adapters
Implementation of Z-BERT-A: a zero-shot pipeline for unknown intent detection.