# Few-Shot Event Detection with Prototypical Amortized Conditional Random Field

arXiv: https://arxiv.org/abs/2012.02353 · HTML: https://mlsanity.com/paper/2012.02353/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2020.

## Built on by (most cited first, 20 of 20)

- [DEGREE: A Data-Efficient Generation-Based Event Extraction Model](https://mlsanity.com/paper/2108.12724/) (2021)
- [The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation](https://mlsanity.com/paper/2306.06918/) (2023)
- [Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors](https://mlsanity.com/paper/2404.17807/) (2024)
- [A Survey on Deep Learning Event Extraction: Approaches and Applications](https://mlsanity.com/paper/2107.02126/) (2021)
- [Information Extraction in Low-Resource Scenarios: Survey and Perspective](https://mlsanity.com/paper/2202.08063/) (2022)
- [Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention](https://mlsanity.com/paper/2109.05747/) (2021)
- [The Art of Prompting: Event Detection based on Type Specific Prompts](https://mlsanity.com/paper/2204.07241/) (2022)
- [Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification](https://mlsanity.com/paper/2108.12844/) (2021)
- [Few-shot Event Detection: An Empirical Study and a Unified View](https://mlsanity.com/paper/2305.01901/) (2023)
- [Targeted Augmentation for Low-Resource Event Extraction](https://mlsanity.com/paper/2405.08729/) (2024)
- [Event Extraction: A Survey](https://mlsanity.com/paper/2210.03419/) (2022)
- [Type Information Utilized Event Detection via Multi-Channel GNNs in Electrical Power Systems](https://mlsanity.com/paper/2211.08168/) (2022)
- [HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold](https://mlsanity.com/paper/2210.08806/) (2022)
- [Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning](https://mlsanity.com/paper/2305.17373/) (2023)
- [Few-shot Named Entity Recognition with Cloze Questions](https://mlsanity.com/paper/2111.12421/) (2021)
- [P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization](https://mlsanity.com/paper/2202.07615/) (2022)
- [MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection](https://mlsanity.com/paper/2305.09335/) (2023)
- [Mutually Guided Few-shot Learning for Relational Triple Extraction](https://mlsanity.com/paper/2306.13310/) (2023)
- [Few-shot Incremental Event Detection](https://mlsanity.com/paper/2209.01979/) (2022)
- [Class-Incremental Few-Shot Event Detection](https://mlsanity.com/paper/2404.01767/) (2024)

## Abstract (arXiv)

Event detection tends to struggle when it needs to recognize novel event types with a few samples. The previous work attempts to solve this problem in the identify-then-classify manner but ignores the trigger discrepancy between event types, thus suffering from the error propagation. In this paper, we present a novel unified model which converts the task to a few-shot tagging problem with a double-part tagging scheme. To this end, we first propose the Prototypical Amortized Conditional Random Field (PA-CRF) to model the label dependency in the few-shot scenario, which approximates the transition scores between labels based on the label prototypes. Then Gaussian distribution is introduced for modeling of the transition scores to alleviate the uncertain estimation resulting from insufficient data. Experimental results show that the unified models work better than existing identify-then-classify models and our PA-CRF further achieves the best results on the benchmark dataset FewEvent. Our code and data are available at http://github.com/congxin95/PA-CRF.