arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.13282cs.CLcs.LG
收藏

基于大语言模型的桥梁设计规范问答系统

Question answering system of bridge design specification based on large language model

Jiangsu College of Finance & Accounting(江苏财会职业学院);Wanshi Antecedence Digital Intelligence Traffic Technology Co., Ltd(万氏先行数智交通科技有限公司)

Leye Zhang, Xiangxiang Tian, Hongjun Zhang

AI总结:

本文构建了基于大语言模型的桥梁设计规范问答系统,对比了Bert模型的全量微调、参数高效微调及从零自建模型三种方案,发现全量微调在所有数据集上达到100%准确率,为专业领域问答系统开发提供了参考。

摘要:

本文构建了基于大语言模型的桥梁设计规范问答系统。尝试了三种实现方案:Bert预训练模型的全量微调、Bert预训练模型的参数高效微调,以及从零自建语言模型。通过自建的问答任务数据集,基于tensorflow和keras深度学习平台框架,构建并训练模型,以预测用户给出的桥梁设计规范中答案的起始位置和结束位置。实验结果表明,Bert预训练模型的全量微调在训练数据集、验证数据集和测试数据集中均达到100%的准确率,系统能从用户给出的桥梁设计规范中提取答案以回答用户的各种问题;而Bert预训练模型的参数高效微调和从零自建语言模型在训练数据集中表现良好,但它们在测试数据集中的泛化能力有待提高。本文的研究为专业领域问答系统的开发提供了有益参考。

英文摘要:

This paper constructs question answering system for bridge design specification based on large language model. Three implementation schemes are tried: full fine-tuning of the Bert pretrained model, parameter-efficient fine-tuning of the Bert pretrained model, and self-built language model from scratch. Through the self-built question and answer task dataset, based on the tensorflow and keras deep learning platform framework, the model is constructed and trained to predict the start position and end position of the answer in the bridge design specification given by the user. The experimental results show that full fine-tuning of the Bert pretrained model achieves 100% accuracy in the training-dataset, validation-dataset and test-dataset, and the system can extract the answers from the bridge design specification given by the user to answer various questions of the user; While parameter-efficient fine-tuning of the Bert pretrained model and self-built language model from scratch perform well in the training-dataset, their generalization ability in the test-dataset needs to be improved. The research of this paper provides a useful reference for the development of question answering system in professional field.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑