Storyline trees are hierarchical narrative representations built via top-down and bottom-up inference on scene segments that support adaptive retrieval and outperform baselines on three long-form QA benchmarks.
Is semantic chunking worth the computational cost?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Recursive character-based chunking at 300 characters outperforms Sentence-Based, Khmer-Aware, and LLM-Based methods on L2 distance, answer relevance, and Khmer IoU in a 5-fold evaluation on 18 Khmer agricultural QA pairs.
citing papers explorer
-
Storyline Trees: Hierarchical Representations for Long-Form Narratives
Storyline trees are hierarchical narrative representations built via top-down and bottom-up inference on scene segments that support adaptive retrieval and outperform baselines on three long-form QA benchmarks.
-
Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents
Recursive character-based chunking at 300 characters outperforms Sentence-Based, Khmer-Aware, and LLM-Based methods on L2 distance, answer relevance, and Khmer IoU in a 5-fold evaluation on 18 Khmer agricultural QA pairs.