OpenAutoNLU: Open Source AutoML Library for NLU
About
OpenAutoNLU is an open-source automated machine learning library for natural language understanding (NLU) tasks, covering both text classification and named entity recognition (NER). Unlike existing solutions, we introduce data-aware training regime selection that requires no manual configuration from the user. The library also provides integrated data quality diagnostics, configurable out-of-distribution (OOD) detection, and large language model (LLM) features, all within a minimal lowcode API. The demo app is accessible here https://openautonlu.dev.
Grigory Arshinov, Aleksandr Boriskin, Sergey Senichev, Ayaz Zaripov, Daria Galimzianova, Daniil Karpov, Leonid Sanochkin• 2026
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Intent Classification | MASSIVE (full) | F1-Macro87.6 | 5 | |
| Intent Classification | SNIPS (full) | F1-Macro92.1 | 5 | |
| Out-of-Distribution Intent Detection | Banking77 | F1-Macro91.2 | 5 | |
| Out-of-Distribution Intent Detection | HWU64 | F1-Macro89.3 | 5 | |
| Out-of-Distribution Intent Detection | MASSIVE | F1-Macro87.6 | 5 | |
| Out-of-Distribution Intent Detection | SNIPS | F1-Macro92.8 | 5 | |
| Intent Classification | Banking77 (full) | F1-Macro91.2 | 5 | |
| Intent Classification | HWU64 (full) | F1-Macro89 | 5 |
Showing 8 of 8 rows