A Text Classification-based Approach for Evaluating and Enhancing the Machine Interpretability of Building Codes
发表于 Engineering Applications of Artificial Intelligence, 2023
本研究基于团队领域大语言模型成果,提出一种高效的规范条文分类及规范可解译性评价方法;结果表明所提出的算法F1指标为93.6%、显著优于既有方法,且可进一步将升下游规则自动解译算法提升4%;研究同时表明现有规范的整体机器可解译性仅有34.4%,亟需从人-机双方角度改进规范编写方法及规则解译算法,实现完全自动化的规范解析
引用方式: Zheng, Z., Zhou, Y.C., Chen, K.Y., Lu, X.Z., She, Z.T., Lin, J.R.* (2024). A Text Classification-based Approach for Evaluating and Enhancing the Machine Interpretability of Building Codes. Engineering Applications of Artificial Intelligence, 127, 107207. doi: 10.1016/j.engappai.2023.107207 http://doi.org/10.1016/j.engappai.2023.107207