PILED: An Identify-and-Localize Framework for Few-Shot Event Detection

• URL: http://arxiv.org/abs/2202.07615v1
• Date: Tue, 15 Feb 2022 18:01:39 GMT
• Title: PILED: An Identify-and-Localize Framework for Few-Shot Event Detection
• Authors: Sha Li, Liyuan Liu, Yiqing Xie, Heng Ji, Jiawei Han
• Abstract summary: In our study, we employ cloze prompts to elicit event-related knowledge from pretrained language models. We minimize the number of type-specific parameters, enabling our model to quickly adapt to event detection tasks for new types.
• Score: 79.66042333016478
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Practical applications of event extraction systems have long been hindered by their need for heavy human annotation. In order to scale up to new domains and event types, models must learn to cope with limited supervision, as in few-shot learning settings. To this end, the major challenge is to let the model master the semantics of event types, without requiring abundant event mention annotations. In our study, we employ cloze prompts to elicit event-related knowledge from pretrained language models and further use event definitions and keywords to pinpoint the trigger word. By formulating the event detection task as an identify-then-localize procedure, we minimize the number of type-specific parameters, enabling our model to quickly adapt to event detection tasks for new types. Experiments on three event detection benchmark datasets (ACE, FewEvent, MAVEN) show that our proposed method performs favorably under fully supervised settings and surpasses existing few-shot methods by 21% F1 on the FewEvent dataset and 20% on the MAVEN dataset when only 5 examples are provided for each event type.

Related papers

• Improving Event Definition Following For Zero-Shot Event Detection [66.27883872707523]
  Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types. We aim to improve zero-shot event detection by training models to better follow event definitions.
  arXiv  Detail & Related papers  (2024-03-05T01:46:50Z)
• Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning [45.3385722995475]
  We propose MetaEvent, a meta learning-based framework for zero- and few-shot event detection. In our framework, we propose to use the cloze-based prompt and a trigger-aware softr to efficiently project output to unseen event types. As such, the proposed MetaEvent can perform zero-shot event detection by mapping features to event types without any prior knowledge.
  arXiv  Detail & Related papers  (2023-05-27T05:36:46Z)
• Few-shot Incremental Event Detection [3.508346077709686]
  Event detection tasks can enable the quick detection of events from texts. To extend them to detect a new class without losing the ability to detect old classes requires costly retraining of the model from scratch. We define a new task, few-shot incremental event detection, which focuses on learning to detect a new event class with limited data.
  arXiv  Detail & Related papers  (2022-09-05T14:21:26Z)
• The Art of Prompting: Event Detection based on Type Specific Prompts [28.878630198163556]
  We develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. Our framework shows up to 24.3% F-score gain over the previous state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-14T21:28:50Z)
• Learning Constraints and Descriptive Segmentation for Subevent Detection [74.48201657623218]
  We propose an approach to learning and enforcing constraints that capture dependencies between subevent detection and EventSeg prediction. We adopt Rectifier Networks for constraint learning and then convert the learned constraints to a regularization term in the loss function of the neural model.
  arXiv  Detail & Related papers  (2021-09-13T20:50:37Z)
• Unsupervised Label-aware Event Trigger and Argument Classification [73.86358632937372]
  We propose an unsupervised event extraction pipeline, which first identifies events with available tools (e.g., SRL) and then automatically maps them to pre-defined event types. We leverage pre-trained language models to contextually represent pre-defined types for both event triggers and arguments. We successfully map 83% of the triggers and 54% of the arguments to the correct types, almost doubling the performance of previous zero-shot approaches.
  arXiv  Detail & Related papers  (2020-12-30T17:47:24Z)
• Extensively Matching for Few-shot Learning Event Detection [66.31312496170139]
  Event detection models under super-vised learning settings fail to transfer to new event types. Few-shot learning has not beenexplored in event detection. We propose two novelloss factors that matching examples in the sup-port set to provide more training signals to themodel.
  arXiv  Detail & Related papers  (2020-06-17T18:30:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.