From coarse to fine: Enhancing multi-document summarization with multi-granularity relationship-based extractor

计算机科学 自动汇总 粒度 判决 冗余(工程) 图形 情报检索 可读性 集合(抽象数据类型) 数据挖掘 人工智能 理论计算机科学 程序设计语言 操作系统
作者
Ming Zhang,J.P. Lu,Jiahao Yang,Jun Zhou,Meilin Wan,Xuejun Zhang
出处
期刊:Information Processing and Management [Elsevier BV]
卷期号:61 (3): 103696-103696 被引量:8
标识
DOI:10.1016/j.ipm.2024.103696
摘要

Multi-Document Summarization (MDS) is a challenging task due to the fact that multiple documents not only have extremely long inputs but may also be overlapping, complementary, or contradictory to each other. In this paper, we propose to capture complex cross-document interactions to handle lengthy inputs for better multi-document summarization. Specifically, we present MDS-MGRE, a coarse-to-fine MDS framework that introduces Multi-Granularity Relationships into an Extract-then-summarize pipeline. In the coarse-grained stage, multi-granularity embedding, heterogeneous graph construction, and MGRExtractor work together to convert redundant multi-documents into compact meta-documents. We first utilize pre-trained language model BERT to obtain semantically rich embeddings for documents at different granularities, including documents, paragraphs, sentence-sets, and sentences. Then, we construct a heterogeneous graph with 4 types of nodes (document nodes, paragraph nodes, sentence-set nodes, and sentence nodes) and corresponding connecting edges to model rich document relationships. Furthermore, we propose a novel Multi-Granularity Relationship-based Extractor (MGRExtractor) to produce meta-documents by efficiently pruning heterogeneous graphs. More precisely, it consists of 4 main modules: noise removal, redundancy removal, multi-granularity scoring, and sentence-set selection. In the fine-grained stage, we employ the large configuration of BART as our abstractive summarizer to generate system summaries from the extracted meta-documents. Experimental results on two benchmark datasets show that our framework significantly outperforms strong baselines with comparable parameters, and slightly underperforms methods with a maximum encoding length of 16,384 tokens. For Multi-News and WCEP, automatic evaluation results show that MDS-MGRE achieves an average performance improvement of 1.75% and 8.77% compared to the state-of-the-art systems with comparable parameters, respectively. Such positive results demonstrate the benefits of generating high-quality meta-documents to enhance MDS by modeling rich document relationships.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
skylar完成签到,获得积分10
刚刚
敏感寻真发布了新的文献求助10
刚刚
李爱国的应助被月月采纳,获得30
刚刚
青筝完成签到,获得积分10
刚刚
1秒前
李付清发布了新的文献求助10
1秒前
1秒前
Jasper的应助被jayna采纳,获得10
1秒前
YEFEIeee发布了新的文献求助10
1秒前
Alice发布了新的文献求助10
2秒前
2秒前
2秒前
2秒前
zzk发布了新的文献求助10
3秒前
3秒前
4秒前
今天看文献了吗完成签到,获得积分10
4秒前
Ascho发布了新的文献求助10
4秒前
初景发布了新的文献求助10
4秒前
Winnie完成签到,获得积分10
4秒前
liangliang发布了新的文献求助10
4秒前
蜡笔小鑫完成签到,获得积分10
4秒前
聚乙二醇发布了新的文献求助10
5秒前
科研通AI6.4的应助被wei采纳,获得10
5秒前
Allen发布了新的文献求助10
5秒前
爱听歌的向卉完成签到,获得积分10
6秒前
亚鲁完成签到,获得积分10
6秒前
朱妙彤发布了新的文献求助10
6秒前
newboy_wxs完成签到,获得积分10
6秒前
lcj1014发布了新的文献求助10
6秒前
7秒前
pan关注了科研通微信公众号
7秒前
8秒前
Abracadabra的应助被矜持采纳,获得10
8秒前
8秒前
香蕉觅云的应助被李言新采纳,获得10
8秒前
fjy123发布了新的文献求助10
8秒前
小欣完成签到,获得积分10
8秒前
wei完成签到,获得积分10
9秒前
王11发布了新的文献求助30
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Markov Decision Processes and Reinforcement Learning 700
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8170564
求助须知:如何正确求助?哪些是违规求助? 9563327
关于积分的说明 21770091
捐赠科研通 7762045
什么是DOI,文献DOI怎么找? 3430706
关于科研通互助平台的介绍 2554553
邀请新用户注册赠送积分活动 2475466