检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:黄东晋 秦汉 郭昊 HUANG Dong-jin;QIN Han;GUO Hao(Shanghai Film Academy,Shanghai University,Shanghai 200072,China)
出 处:《计算机技术与发展》2020年第11期158-162,共5页Computer Technology and Development
基 金:国家自然科学基金(61402278);上海市自然科学基金(19ZR1419100);上海大学电影学高峰学科项目(19ZR1419100)。
摘 要:智能问答是自然语言处理领域一个非常重要的研究热点,传统的智能问答不能准确地理解用户的意图,从而无法返回准确的答案。因此,提出了基于BERT-CNN算法的智能问答系统,并应用于电影原声领域,可以快速准确地反馈相关信息。首先,构建电影原声的知识图谱,建立节点实体以及实体之间的关系,利用Neo4j图数据库对数据进行存储。然后,通过基于规则和词典的方法进行实体识别,利用BERT-CNN分类算法对用户意图进行分类。最后,根据用户意图和实体,将问句转化成知识图谱的查询语句,在数据库中查询后返回结果。实验结果表明,构建的面向电影原声智能问答系统是可行的,采用BERT-CNN分类算法,分类准确率高达91.24%,能够实时得到问题答案的准确反馈,准确率达到95%以上。Intelligent question answering is a quite important research hotspot in the field of natural language processing.Traditional intelligent question answering cannot accurately understand the user’s intention,so it cannot return accurate answers.Therefore,an intelligent question-and-answer system based on BERT-CNN algorithm is proposed and applied to the field of movie soundtrack,which can feedback relevant information quickly and accurately.First,the knowledge map of movie soundtrack is constructed,node entities and relationship between entities are established,and Neo4j graph database is used to store the data.Then,entity recognition is carried out based on rules and dictionaries,and user intention is classified by BERT-CNN classification algorithm.Finally,according to user intention and entity,the question is transformed into the query statement of knowledge graph,and the result is returned after the query in the database.The experiment shows that the constructed intelligent question-and-answer system oriented to the film soundtrack is feasible.The BERT-CNN classification algorithm is adopted,with the classification accuracy as high as 91.24%,and the accurate feedback of the questions can be obtained in real time,with the accuracy of more than 95%.
关 键 词:智能问答 知识图谱 电影原声 BERT-CNN分类 图数据库
分 类 号:TP31[自动化与计算机技术—计算机软件与理论]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:13.59.210.36