Multistage Mixed-Attention Unsupervised Keyword Extraction for Summary Generation

Author:

Wu Di1,Cheng Peng1ORCID,Zheng Yuying1

Affiliation:

1. School of Information and Electronic Engineering, Hebei University of Engineering, No. 19 Taiji Road, Handan 056000, China

Abstract

Summary generation is an important research direction in natural language processing. Aimed at the problems of redundant information processing difficulties and an inability to generate high-quality summaries from long text in existing summary generation models, BART is the backbone model, an N + 1 coarse–fine-grained multistage summary generation framework is constructed, and a multistage mixed-attention unsupervised keyword extraction summary generation model is proposed (multistage mixed-attention unsupervised keyword extraction for summary generation, MSMAUKE-SummN). In the N-coarse-grained summary generation stages, a sentence filtering layer (PureText) is constructed to remove redundant information in long text. A mixed-attention unsupervised approach is used to iteratively extract keywords, assisting summary inference and enriching the global semantic information of coarse-grained summaries. In the 1-fine-grained summary generation stage, a self-attentive keyword selection module (KeywordSelect) is designed to obtain keywords with higher weights and enhance the local semantic representation of fine-grained summaries. Tandem N-coarse-grained and 1-fine-grained summary generation stages are used to obtain long text summaries through a multistage generation approach. The experimental results show that the model improves the ROUGE-1, ROUGE-2, and ROUGE-L metrics by a minimum of 0.75%, 1.48%, and 1.25% over the HMNET, TextRank, HAT-BART, DDAMS, and SummN models on summarized datasets such as AMI, ICSI, and QMSum.

Funder

Research Projects of the Nature Science Foundation of Hebei Province

National Natural Science Foundation of China

Publisher

MDPI AG

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3