Summary of Degap: Dual Event-guided Adaptive Prefixes For Templated-based Event Argument Extraction with Slot Querying, by Guanghui Wang et al.
DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying
by Guanghui Wang, Dexi Liu, Jian-Yun Nie, Qizhi Wan, Rong Hu, Xiping Liu, Wanlong Liu, Jiaming Liu
First submitted to arxiv on: 22 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
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 research paper proposes a novel approach to event argument extraction (EAE) called DEGAP. The method tackles two challenges in current EAE models by incorporating auxiliary information during training and inference. Specifically, DEGAP uses dual prefixes: instance-oriented and template-oriented prompt vectors trained on different event instances and templates. Additionally, the authors introduce an event-guided adaptive gating mechanism that leverages connections between events to capture relevant information. Experimental results demonstrate state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). The proposed method provides cues for EAE models without requiring retrieval. DEGAP’s components are shown to have a significant impact on the model’s performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Scientists are working on a new way to understand how events work together. They’re trying to improve “event argument extraction” by using extra information to help with this task. The problem is that current methods don’t always find relevant information and also create templates for each event without thinking about how they might be connected. This paper proposes a solution called DEGAP, which uses two types of prompts (instance-oriented and template-oriented) and an adaptive mechanism to learn from different events. The results show that this method is the best so far on four different datasets. |
Keywords
» Artificial intelligence » Inference » Prompt
