用词、句、语义三类特征构建无需外部模型的图结构，提升长文档摘要效果。
GraphLSS: Integrating Lexical, Structural, and Semantic Features for Long Document Extractive Summarization
- 构建包含词与句两级信息的异构图，四类边直接由原文特征定义
- 在两个基准数据集上性能媲美顶尖图模型，超越非图基方法
- 无需额外工具或训练模型，结构清晰可解释，适合文本摘要研究者
异构图神经网络近年来被用于长文档摘要任务，将摘要抽取建模为节点分类问题。尽管有效，这些方法常需依赖外部工具或额外机器学习模型来构建图结构，导致结构复杂且不够直观。本文提出GraphLSS，一种用于长文档抽取式摘要的异构图构建方法，融合词汇、结构与语义特征。该方法定义了词与句两个层次的信息，并构建四类边：句子语义相似性、句子出现顺序、词在句中关系、词语义相似性，完全不依赖辅助学习模型。在两个基准数据集上的实验表明，GraphLSS在性能上可与当前最先进的图方法相媲美，且优于近期的非图基模型。代码已开源于GitHub。
原文摘要 · Abstract (English)
Heterogeneous graph neural networks have recently gained attention for long document summarization, modeling the extraction as a node classification task. Although effective, these models often require external tools or additional machine learning models to define graph components, producing highly complex and less intuitive structures. We present GraphLSS, a heterogeneous graph construction for long document extractive summarization, incorporating Lexical, Structural, and Semantic features. It defines two levels of information (words and sentences) and four types of edges (sentence semantic similarity, sentence occurrence order, word in sentence, and word semantic similarity) without any need for auxiliary learning models. Experiments on two benchmark datasets show that GraphLSS is competitive with top-performing graph-based methods, outperforming recent non-graph models. We release our code on GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。