PulseAugur
LIVE 16:59:48
research · [1 source] ·
0
research

Researchers introduce EXCEEDS for complex event extraction in scientific domains

Researchers have introduced EXCEEDS, a novel framework designed for extracting complex events from scientific documents. To address the unique challenges of scientific text, such as dense information and intricate event structures, they also developed SciEvents, a large-scale dataset featuring over 24,000 events annotated across 2,508 documents. The EXCEEDS framework models dense nuggets within a grid matrix, simplifying the extraction process. Experiments show EXCEEDS achieves state-of-the-art performance on the SciEvents dataset, with both the dataset and framework made publicly available. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Provides a new dataset and framework to improve information extraction from scientific literature, potentially accelerating research.

RANK_REASON The cluster contains an academic paper introducing a new method and dataset for event extraction in the scientific domain.

Read on arXiv cs.CL →

COVERAGE [1]

  1. arXiv cs.CL TIER_1 · Yi-Fan Lu, Xian-Ling Mao, Bo Wang, Xiao Liu, Heyan Huang ·

    EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain

    arXiv:2406.14075v2 Announce Type: replace Abstract: It is crucial to understand a specific domain by events. Extensive event extraction research has been conducted in many domains such as news, finance, and biology. However, event extraction in scientific domain is still insuffic…