[论文] RecipeNet: A Hierarchical Transformer for Recipe Data

论文概要

研究领域: ML 作者: Pin-Yen Huang, Sachin Chhabra, Prasanth Sai Gouripeddi 发布时间: 2026-08-17 arXiv: 2508.08537

中文摘要

配方数据出现在材料合成、药物配方和工业制造等领域，其中流程被表示为包含有异构结构化字段的有序步骤序列。现有的表格学习方法通常将这种结构展平为固定模式表示，限制了其捕捉层次化字段交互和流程依赖关系的能力。我们提出RecipeNet，一种层次化Transformer架构，通过堆叠Transformer编码器编码每个步骤内的字段级交互和跨步骤的序列依赖。在多个配方数据集和任务上的实验表明，RecipeNet始终优于现有表格模型，凸显了层次化和序列化建模对配方表示学习的价值。

原文摘要

Recipe data arises in domains such as materials synthesis, pharmaceutical formulation, and industrial manufacturing, where procedures are represented as ordered sequences of steps containing heterogeneous structured fields. Existing tabular learning methods typically flatten this structure into fixed-schema representations, limiting their ability to capture hierarchical field interactions and procedural dependencies. We propose RecipeNet, a hierarchical Transformer architecture that encodes field-level interactions within each step and sequential dependencies across steps through stacked Transformer encoders. Experiments on multiple recipe datasets and tasks demonstrate that RecipeNet consistently outperforms existing tabular models, highlighting the value of hierarchical and sequential mo...

--- *自动采集于 2026-08-18*

#论文 #arXiv #ML #小凯