AutoIntent: AutoML for Text Classification
About
AutoIntent is an automated machine learning tool for text classification tasks. Unlike existing solutions, AutoIntent offers end-to-end automation with embedding model selection, classifier optimization, and decision threshold tuning, all within a modular, sklearn-like interface. The framework is designed to support multi-label classification and out-of-scope detection. AutoIntent demonstrates superior performance compared to existing AutoML tools on standard intent classification datasets and enables users to balance effectiveness and resource consumption.
Ilya Alekseev, Roman Solomatin, Darina Rustamova, Denis Kuznetsov• 2025
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Intent Classification | SNIPS (full) | F1-Macro78.6 | 5 | |
| Out-of-Distribution Intent Detection | Banking77 | F1-Macro86.9 | 5 | |
| Out-of-Distribution Intent Detection | HWU64 | F1-Macro82.9 | 5 | |
| Out-of-Distribution Intent Detection | MASSIVE | F1-Macro75.5 | 5 | |
| Out-of-Distribution Intent Detection | SNIPS | F1-Macro82.9 | 5 | |
| Intent Classification | Banking77 (full) | F1-Macro86.9 | 5 | |
| Intent Classification | HWU64 (full) | F1-Macro82.9 | 5 | |
| Intent Classification | MASSIVE (full) | F1-Macro75.5 | 5 |
Showing 8 of 8 rows