{"ID":2869802,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18168","arxiv_id":"2509.18168","title":"HSGM: Hierarchical Segment-Graph Memory for Scalable Long-Text Semantics","abstract":"Semantic parsing of long documents remains challenging due to quadratic growth in pairwise composition and memory requirements. We introduce \\textbf{Hierarchical Segment-Graph Memory (HSGM)}, a novel framework that decomposes an input of length $N$ into $M$ meaningful segments, constructs \\emph{Local Semantic Graphs} on each segment, and extracts compact \\emph{summary nodes} to form a \\emph{Global Graph Memory}. HSGM supports \\emph{incremental updates} -- only newly arrived segments incur local graph construction and summary-node integration -- while \\emph{Hierarchical Query Processing} locates relevant segments via top-$K$ retrieval over summary nodes and then performs fine-grained reasoning within their local graphs. Theoretically, HSGM reduces worst-case complexity from $O(N^2)$ to $O\\!\\left(N\\,k + (N/k)^2\\right)$, with segment size $k \\ll N$, and we derive Frobenius-norm bounds on the approximation error introduced by node summarization and sparsification thresholds. Empirically, on three benchmarks -- long-document AMR parsing, segment-level semantic role labeling (OntoNotes), and legal event extraction -- HSGM achieves \\emph{2--4$\\times$ inference speedup}, \\emph{$\u003e60\\%$ reduction} in peak memory, and \\emph{$\\ge 95\\%$} of baseline accuracy. Our approach unlocks scalable, accurate semantic modeling for ultra-long texts, enabling real-time and resource-constrained NLP applications.","short_abstract":"Semantic parsing of long documents remains challenging due to quadratic growth in pairwise composition and memory requirements. We introduce \\textbf{Hierarchical Segment-Graph Memory (HSGM)}, a novel framework that decomposes an input of length $N$ into $M$ meaningful segments, constructs \\emph{Local Semantic Graphs} o...","url_abs":"https://arxiv.org/abs/2509.18168","url_pdf":"https://arxiv.org/pdf/2509.18168v1","authors":"[\"Dong Liu\",\"Yanxuan Yu\"]","published":"2025-09-17T10:11:02Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}