摘要
自动咨询服务是实现图书馆自动化的重要手段,而传统的图书馆咨询服务系统面临咨询服务满意度较低的问题。针对问题,文章提出基于Bert语义的图书馆自动咨询方法,该方法首先利用问句理解模块对问句进行语义分类,其次采用问句检索模块对读者提出的问题进行匹配,随后通过预训练模型Bert进行答案句生成。在真实的问题数据集上进行测试,文中所提出的方法咨询性能优于传统的咨询方法,准确率有了较大提高。
Automatic consultation service is an important means to realize library automation, but the traditional library consultation service system is faced with the problem of low satisfaction. In order to solve these problems, this paper proposes an automatic library consultation method based on the semantics of Bert. Firstly, this method uses the question understanding module to classify the questions semantically, then uses the question retrieval module to match the questions raised by readers, and then uses the pre-training model, Bert to generate the answer sentences. The performance of the proposed method is better than that of the traditional method, and the accuracy rate is 76%.
出处
《河北科技图苑》
2021年第6期49-53,32,共6页
Hebei Library Journal of Science and Technology
关键词
图书馆
自动咨询
Bert语义
答案生成
Library
Automatic Consultation
Bert Semantics
Answer Generation
