针对传统问答模型采用循环神经网络带来的梯度消失和网络退化的问题,提出一种基于IMGRU-Seq2seq(Identity Mapping Gated Recurrent Unit-Sequence to Sequence)的自动问答模型.通过 TF-IDF 方法对文本进行加权词向量表示;以门控循环单元为基础,将批标准化技术和线性整流激活函数相结合并添加恒等映射,从而构建IMGRU模型;将双向IMGRU作为问答模型的语义抽取单元,引入注意力机制和集束搜索算法,实现自动问答.实验结果表明,所提方法比现有方法BLEU、ROUGE-L分别平均提高18.87％、4.35％.
AUTOMATIC QUESTION ANSWERING METHOD BASED ON IMGRU-SEQ2SEQ
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.
国家科技期刊平台
NSTL
万方数据
