🤖 AI Summary
Traditional multi-document summarization struggles with integrating multi-perspective narrative texts (e.g., legal testimonies, historical accounts) due to its overemphasis on concision, compromising temporal coherence and factual completeness. To address this, we formally introduce *Narrative Consolidation*—a novel task requiring precise chronological ordering, comprehensive content coverage, and seamless integration of complementary details. We propose the Temporal Alignment Event Graph (TAEG), a graph-based model that explicitly unifies event alignment with temporal structure modeling. TAEG incorporates graph centrality measures (e.g., PageRank) to automatically select authoritative narrative versions. Evaluated on the Four Gospels dataset, our method achieves perfect temporal consistency (Kendall’s Tau = 1.000) and improves ROUGE-L F1 by 357.2% over baselines, demonstrating that explicit temporal backbone modeling is essential for effective narrative consolidation.
📝 Abstract
Processing overlapping narrative documents, such as legal testimonies or historical accounts, often aims not for compression but for a unified, coherent, and chronologically sound text. Standard Multi-Document Summarization (MDS), with its focus on conciseness, fails to preserve narrative flow. This paper formally defines this challenge as a new NLP task: Narrative Consolidation, where the central objectives are chronological integrity, completeness, and the fusion of complementary details. To demonstrate the critical role of temporal structure in this task, we introduce Temporal Alignment Event Graph (TAEG), a graph structure that explicitly models chronology and event alignment. By applying a standard centrality algorithm to TAEG, our method functions as a version selection mechanism, choosing the most central representation of each event in its correct temporal position. In a study on the four Biblical Gospels, this structure-focused approach guarantees perfect temporal ordering (Kendall's Tau of 1.000) by design and dramatically improves content metrics (e.g., +357.2% in ROUGE-L F1). The success of this baseline method validates the formulation of Narrative Consolidation as a relevant task and establishes that an explicit temporal backbone is a fundamental component for its resolution.