基于T5 PEGASUS和DeepKE的文本摘要生成研究  

Research on Text Abstract Generation Based on T5 PEGASUS and DeepKE

作　　者：张琪 王玲 申杰[2] ZHANG Qi;WANG Ling;SHEN Jie(Henan Vocational College of Water Conservancy and Environment,Zhengzhou 450008,China;North China University of Water Resources and Electric Power,Zhengzhou 450045,China)

机构地区：[1]河南水利与环境职业学院,河南郑州450008 [2]华北水利水电大学,河南郑州450045

出　　处：《电脑与电信》2024年第6期62-67,共6页Computer & Telecommunication

基　　金：河南省2024年科技攻关项目:车载算力网络下多维异构资源智能调度技术研究(242102240133);河南水利与环境职业学院校级项目:基于T5PEGASUS和知识图谱的新闻文本摘要生成研究(SHKYXM2421);河南水利与环境职业学院校级项目:职业教育高水平专业群建设研究与实践——以物联网应用技术专业群为例(SHKYXM2203)。

摘　　要：为减少T5PEGASUS模型生成的摘要中的虚构信息、重复等问题,提出了一种基于T5PEGASUS和DeepKE的文本摘要生成模型——T5PEGASUS-DK。该模型将T5PEGASUS模型和DeepKE框架相融合,先使用Pkuseg分词方法改进分词效果,再使用DeepKE框架抽取文本中的三元组,最后将三元组的词向量集合与文本的表示向量进行拼接。通过建立文本与三元组之间的映射关系,使得模型可以提取出事实性知识,从而提取出与原文内容更相符的信息作为摘要。T5PEGASUS-DK模型的ROUGE值均达到最高,所生成的摘要更真实、连贯,与原文内容更相符。In order to solve the problem of false information and duplication in the summarizations generated by the T5 PEGASUS model,a text summarization model based on T5 PEGASUS and DeepKE-T5 PEGASUS-DK is proposed.This model combines the T5 PEGASUS model with DeepKE framework.Firstly,the Pkuseg segmentation method is used to improve the segmentation performance.Then,the DeepKE framework is used to extract triads from text.Finally,the word vector set of triads is concatenated with the representation vector of text.By establishing a mapping relationship between text and triads,the model can extract factual knowledge and extract information that is more consistent with the original content as a summary.The experimental results show that the T5 PEGASUS-DK model has the highest ROUGE value,and the generated abstracts are more authentic,coherent,and consistent with the original content.

关 键 词：文本摘要生成 T5 PEGASUS DeepKE 三元组 ROUGE 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]