Summary of Harvesting Events From Multiple Sources: Towards a Cross-document Event Extraction Paradigm, by Qiang Gao et al.
Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm
by Qiang Gao, Zixiang Meng, Bobo Li, Jun Zhou, Fei Li, Chong Teng, Donghong Ji
First submitted to arxiv on: 23 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel task called Cross-Document Event Extraction (CDEE) to integrate event information from multiple documents and provide a comprehensive perspective on events. The authors construct a dataset, CLES, containing 20,059 documents and 37,688 mention-level events, where over 70% are cross-document. They also propose a CDEE pipeline with five steps: event extraction, coreference resolution, entity normalization, role normalization, and entity-role resolution. The pipeline achieves an F1 score of about 72% in end-to-end cross-document event extraction, highlighting the challenge of this task. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about how to get a better understanding of what’s happening in documents by looking at multiple documents together. Right now, computers can’t do this very well because they only look at one document at a time. The authors created a new dataset with lots of documents and events that they want to extract information from. They also made a plan for how computers can do this better, and it seems to work pretty well! This will help us learn more about what’s going on in the world. |
Keywords
» Artificial intelligence » Coreference » F1 score
