AutoIntent: AutoML for Text Classification

Ilya Alekseev; Roman Solomatin; Darina Rustamova; Denis Kuznetsov

返回文献探索

Paper · arXiv 2509.21138

AutoIntent: AutoML for Text Classification

Ilya Alekseev, Roman Solomatin, Darina Rustamova, Denis Kuznetsov

37 upvotesSeptember 25, 2025arXiv 预印本

AI 摘要

AutoIntent is an automated machine learning tool for text classification that offers end-to-end automation, including embedding model selection, classifier optimization, and decision threshold tuning, and supports multi-label classification and out-of-scope detection.

embedding model selectionclassifier optimizationdecision threshold tuningmulti-label classificationout-of-scope detection

Abstract

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.