摘要
人工智能这个概念逐渐走入大家的视野。机器学习的发展作为推动这一概念普及的主要推手在这一过程中发挥着很重要的作用。随着计算机计算能力的提升和数据存储成本的降低,深度学习作为机器学习的一个分支近年来发展的越来越迅速。智能问答系统作为自然语言处理方向在人工智能的一大重要研究方向近年来得到了原来越多的重视。本文基于优化基于开放领域问答系统目的,采用了基于新型池化编码器方法,通过和传统基于LSTM编码器比较试验,得出新型池化编码器可以优化问答系统性能的结论。
The concept of artificial intelligence has gradually entered everyone's field of vision.The development of machine learning as a major driver of the popularization of this concept plays an important role in this process.With the improvement of computer computing power and the reduction of data storage costs,deep learning as a branch of machine learning has developed more and more rapidly in recent years.As a natural language processing direction,the intelligent question answering system has received more and more attention in the important research direction of artificial intelligence in recent years.Based on the purpose of optimization based on the open field question answering system,this paper adopts a new pooling encoder method,and compares with the traditional LSTM encoder based test,and concludes that the new pooling encoder can optimize the performance of the question and answer system.
作者
姚千鹤
魏银珍
YAO Qian-he;WEI Yin-zhen(Wuhan Research Institute of Posts and Telecommunications,Wuhan 430074,China)
出处
《电子设计工程》
2019年第8期15-18,23,共5页
Electronic Design Engineering
关键词
池化编码器
问答系统
神经网络
序列模型
pooling encoder
question answering
neural network
sequence model