mts-ai/OpenAutoNLU
An open-source pipeline for training natural language understanding models
This tool helps data scientists and machine learning engineers quickly train natural language understanding (NLU) models for tasks like text classification (e.g., sentiment analysis) and named entity recognition (e.g., extracting product names). You provide your text data for training, and it automatically selects the best training approach based on your dataset size, producing a ready-to-deploy NLU model.
Use this if you need to train text classification or named entity recognition models and want an automated, data-driven workflow that handles different data sizes (from very small to large) without manual method selection.
Not ideal if you need to perform other natural language tasks beyond text classification or named entity recognition, or if you prefer to manually control every low-level detail of your model training process.
Stars
39
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mts-ai/OpenAutoNLU"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
floriankark/cs224n-win2223
Code and written solutions of the assignments of the Stanford CS224N: Natural Language...
ThinamXx/Transformers_NLP
The repository will contain a list of projects which we will work on while reading the books of...
dipanjanS/adv_nlp_workshop_odsc_europe22
Extensive tutorials for the Advanced NLP Workshop in Open Data Science Conference Europe 2020....
ruanchaves/napolab
The Natural Portuguese Language Benchmark (Napolab). Stay up to date with the latest...
mantasu/cs224n
Solutions for CS224n (2022)