跳到正文
arXiv cs.CL· Alexandru Rancea, Ionut Anghel, Tudor Cioara, Ovidiu Anchidin, Ancuta Nemes·· 2 天前AI 评分26

多层 AI 流水线实现自然语言到 BPMN 图生成

A Multi-Layered AI Pipeline for BPMN Generation from Natural Language

AI 导读

一项多层流水线方案可将非结构化自然语言流程描述自动转换为 BPMN 图,整合 Transformer 架构、LLM 与本体填充。其中实体抽取使用微调的 RoBERTa 模型,控制流引擎通过 LLM 推理捕捉非相邻关系,并采用动态 few-shot 策略提升有限数据下的泛化能力。关系抽取任务准确率达 90.7%,并在真实心脏病患者过渡护理流程上完成验证。

正文 · 原文

View PDF

Abstract:The automated transformation of unstructured natural language process descriptions into Business Process Model and Notation (BPMN) diagrams remains a challenging task, due to linguistic ambiguity and the difficulty to detect non-adjacent control-flow relationships. This paper proposes a solution for generating BPMN models from natural language descriptions through a multi-layered pipeline that integrates transformer-based architectures, Large Language Models and ontology population. The proposed method starts with natural language descriptions and separates textual processing, control-flow relation extraction, and structural validation into dedicated components. Entity extraction is performed using a fine-tuned RoBERTa-based transformer model while a control-flow engine captures non-adjacent relationships through LLM-based inference. To improve generalization under limited available data, the approach uses a dynamic few-shot strategy with con- trolled template input construction, enabling improved generalization under limited data availability. Additionally, an ontology population mechanism is introduced to represent the generated process models as semantic knowledge structures. For evaluation purposes we have used from the literature and industry reference processes. Additionally, we have validated the proposed method on a real-world heart disease patients transitional care process, capturing practical constraints and multi-actor collaboration, and serving as an expert-defined benchmark scenario. Experimental results demonstrate strong performance in the relation extraction task, achieving an accuracy of 90.7%, as well as maintaining structural alignment between the generated and reference BPMN models across multiple evaluation scenarios scenarios.
Subjects: Computation and Language (cs.CL)
Cite as: arXiv:2611.18157 [cs.CL]
  (or arXiv:2611.18157v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.18157

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Alexandru Miron Rancea [view email]
[v1] Fri, 13 Nov 2026 13:31:08 UTC (1,776 KB)

来源:arXiv cs.CL · arxiv.org