lgalke/text-clf-baselines
WideMLP for Text Classification
This project helps researchers and developers evaluate text classification models more efficiently. It takes datasets for text classification (like news articles or reviews) and provides code to benchmark different model architectures, including a Bag-of-Words Wide MLP, against established methods like graph neural networks and Transformer models. The primary users are machine learning researchers or NLP engineers who need to compare model performance.
No commits in the last 6 months.
Use this if you are a researcher or developer comparing text classification models and want to quickly set up baselines and experiments for your datasets.
Not ideal if you need a plug-and-play solution for a business application, or if you are not comfortable working with research code and setting up dependencies.
Stars
29
Forks
5
Language
Python
License
MIT
Category
Last pushed
Aug 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/lgalke/text-clf-baselines"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
urchade/GLiNER
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from...
HySonLab/ViDeBERTa
ViDeBERTa: A powerful pre-trained language model for Vietnamese, EACL 2023
stccenter/Comparative-Analysis-of-BERT-and-GPT-for-Classifying-Crisis-News-with-Sudan-Conflict-as-an-Example
Comparative Analysis of BERT and GPT for Conflict-Related Multiclass Label Classification from...
NLP-AI-Wizards/clef2025-checkthat
Challenge to distinguish whether a sentence from a news article expresses the subjective view of...
NoisyStudents/NoisyABSA
Domain generalization on Aspect Based Sentiment Analysis (ABSA) task via utilizing noisy student...