arxiv:2603.01824

OpenAutoNLU: Open Source AutoML Library for NLU

Published on Mar 2

· Submitted by

daria galimzianova on Mar 3

MTSAIR

Upvote

Authors:

Grigory Arshinov ,

Aleksandr Boriskin ,

Sergey Senichev ,

Daria Galimzianova ,

Abstract

OpenAutoNLU is an open-source automated machine learning library for NLU tasks that employs data-aware training selection and includes integrated diagnostics and LLM features through a minimal low-code interface.

AI-generated summary

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.

View arXiv page View PDF Project page GitHub 21 Add to collection

Community

daria0gal

Paper author Paper submitter about 9 hours ago

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 low-code API. OpenAutoNLU source code is available here, the demo app is accessible here at https://openautonlu.dev.