计算机应用与软件2024，Vol.41Issue(6)：215-222,256,9.DOI:10.3969/j.issn.1000-386x.2024.06.032
基于IMGRU-Seq2seq的自动问答方法研究
AUTOMATIC QUESTION ANSWERING METHOD BASED ON IMGRU-SEQ2SEQ
摘要
Abstract
Aimed at the problem of gradient disappearance and network degradation caused by the use of recurrent neural networks in traditional question answering models,an automatic question answering model based on IMGRU-Seq2seq(Identity Mapping Gated Recurrent Unit-Sequence to Sequence)is proposed.The text was represented by weighted word vectors through the TF-IDF method.Based on the gated recurrent unit,the batch normalization technology and the rectified linear unit activation function were combined and the identity mapping was added to construct the IMGRU model.As the semantic extraction unit of the question answering model,the bidirectional IMGRU introduced the attention mechanism and the beam search algorithm to realize automatic question and answer.The experimental results show that the proposed method is 18.87％and 4.35％higher than the existing methods BLEU and ROUGE-L respec-tively.关键词
问答模型/门控循环单元神经网络/恒等映射/注意力机制/集束搜索算法Key words
Question answering model/Gated recurrent unit(GRU)/Identity mapping/Attention mechanism/Beam search algorithm分类
信息技术与安全科学引用本文复制引用
姜雨娇,黄铝文,荚子萌..基于IMGRU-Seq2seq的自动问答方法研究[J].计算机应用与软件,2024,41(6):215-222,256,9.基金项目
陕西省农技推广服务重大专项(2016XXPT-00) （2016XXPT-00）
杨凌示范区综合产业项目(2018GY-01) （2018GY-01）
西北农林科技大学校科技创新与成果转换项目(TGZX2019-12). （TGZX2019-12）
