AI RESEARCH

From Global to Local: Learning Context-Aware Graph Representations for Document Classification and Summarization

arXiv CS.CL

ArXi:2603.00021v2 Announce Type: replace Recent NLP systems commonly represent documents as linear token sequences. Although this captures sequential order, it can hinder modeling long-range dependencies and global document structure, especially for long texts. This paper proposes a data-driven method to automatically construct graph-based document representations.