开源NLU自动化工具，自动选训练策略，无需手动调参
OpenAutoNLU: Open Source AutoML Library for NLU
- 根据数据特征自动选择最优训练方案
- 内置数据质量诊断与异常检测功能
- 低代码接口，支持大模型特性，适合快速部署
OpenAutoNLU 是一个面向自然语言理解（NLU）任务的开源自动化机器学习库，涵盖文本分类与命名实体识别（NER）。与现有方案不同，该库引入了无需用户手动配置的数据感知训练策略选择机制。同时提供集成的数据质量诊断、可配置的分布外（OOD）检测以及大语言模型（LLM）功能，均通过极简低代码API实现。演示应用可通过 https://openautonlu.dev 访问。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。