The Art of Prompting: Event Detection based on Type Specific Prompts

By Sijia Wang, Mo Yu, Lifu Huang. 2022

33 citations recorded by the source corpus.

We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental results demonstrate that a well-defined and comprehensive event type prompt can significantly improve event detection performance, especially when the annotated data is scarce (few-shot event detection) or not available (zero-shot event detection). By leveraging the semantics of event types, our unified framework shows up to 22.2% F-score gain over the previous state-of-the-art baselines.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jan Marco Leimeister
2. Ying Shen
3. Zhiyang Xu
4. Antonia Tolzin
5. Lifu Huang
6. Andreas Janson
7. Nils Knoth

Citations in the corpus

• AI literacy and its implications for prompt engineering strategies (2024, background): “However, research in prompt engineering advancements is largely lacking these perspectives until now (Wang, Yu, & Huang, 2022; Zam-firescu-Pereira et al., 2023).”
• MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning (2022, background): “Prompt tuning (Liu et al., 2021; Li and Liang, 2021; Han et al., 2022; Wang et al., 2022b; Sanh et al., 2022) aims to learn a task-specific prompt by reformulating the downstream tasks to the format that the model was initially trained on and has shown competitive performance across various natural…”