PoKE: A Prompt-based Knowledge Eliciting Approach for Event Argument Extraction
This work addresses event extraction, a complex NLP task, by improving accuracy and efficiency, though it appears incremental as it builds on existing prompt-based methods.
The paper tackles event argument extraction by proposing a prompt-based knowledge eliciting approach that leverages both independent and joint event knowledge, achieving superior performance over recent advanced methods on the ACE2005 dataset in fully-supervised and low-resource scenarios.
Eliciting knowledge from pre-trained language models via prompt-based learning has shown great potential in many natural language processing tasks. Whereas, the applications for more complex tasks such as event extraction are less studied since the design of prompt is not straightforward for the structured event containing various triggers and arguments. % Meanwhile, current conditional generation methods employ large encoder-decoder models, which are costly to train and serve. In this paper, we present a novel prompt-based approach, which elicits both the independent and joint knowledge about different events for event argument extraction. The experimental results on the benchmark ACE2005 dataset show the great advantages of our proposed approach. In particular, our approach is superior to the recent advanced methods in both fully-supervised and low-resource scenarios.