摘要
长文本中的信息压缩和语义连贯性一直是摘要生成模型的难点.为此本文提出了一种融合内容引导与多尺度注意力的摘要生成模型.该模型通过双分支结构实现对多粒度语义的联合建模,并利用内容引导机制聚焦于摘要相关的关键信息区域.模型在传统BERT-Transformer架构基础上引入双分支结构增强语义表达能力,并通过MSAA-SAM融合机制设计,进一步实现跨分支信息对齐与表达统一.同时,本文对指针生成网络进行了改进,结合全局句向量引导机制提升生成控制能力,从而增强对长文本中关键信息的提取与冗余内容的抑制.在NLPCC 2017数据集和LCSTS数据集上的实验结果表明,该模型在生成式摘要任务上均优于主流基线模型,验证了其在语义建模、生成质量与控制能力方面的综合优势.
Information compression and semantic coherence in long texts are persistent challenges in summary generation models.To address this issue,this study proposes a summary generation model integrating content-guided and multi-scale attention.The model adopts a dual-branch architecture to jointly model multi-granularity semantics and utilizes a contentguided mechanism to focus on key information relevant to the summary.Based on the conventional BERT-Transformer framework,a dual-branch structure is introduced to enhance semantic representation,and a cross-branch fusion mechanism(MSAA-SAM)is designed to achieve semantic alignment and unified representation.In addition,the pointergenerator network is improved by incorporating a global sentence vector guidance mechanism to enhance generation control,thereby improving key information extraction and reducing redundancy in long-text summarization.Experimental results on the NLPCC 2017 and LCSTS datasets demonstrate that the proposed model outperforms mainstream baseline models in generative summarization tasks,verifying its comprehensive advantages in semantic modeling,generation quality,and control capability.
作者
岳帅
王业
YUE Shuai;WANG Ye(College of Computer and Information Engineering,Xinjiang Agricultural University,Urumqi 830052,China;Network and Information Technology Center,Xinjiang Agricultural University,Urumqi 830052,China)
出处
《计算机系统应用》
2026年第1期276-287,共12页
Computer Systems & Applications
关键词
深度学习
文本摘要
多尺度注意力
内容引导机制
指针生成网络
语义建模
deep learning
text summary
multi-scale attention
content-guided mechanism
pointer-generator network
semantic modeling
