OpenAutoNLU: Open Source AutoML Library for NLU

TL;DR

OpenAutoNLU is an open-source AutoML library designed for NLU tasks, offering automated training, data diagnostics, OOD detection, and LLM features within a user-friendly low-code interface.

Contribution

It introduces a data-aware training regime selection and integrated diagnostics, enhancing automation and usability over existing NLU AutoML solutions.

Findings

Automates NLU model training without manual configuration

Provides integrated data diagnostics and OOD detection

Supports LLM features within a minimal API

Abstract

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.