Eliciting Knowledge from Language Models for Event Extraction

Eliciting knowledge contained in language models via prompt-based learning has shown great potential in many natural language processing tasks, such as text classification and generation. Whereas, the applications for more complex tasks such as event extraction are less studied, since the design of prompt is not straightforward due to the complicated types and arguments. In this paper, we explore to elicit the knowledge from pre-trained language models for event trigger detection and argument extraction. Specifically, we present various joint trigger/argument prompt methods, which can elicit more complementary knowledge by modeling the interactions between different triggers or arguments. The experimental results on the benchmark dataset, namely ACE2005, show the great advantages of our proposed approach. In particular, our approach is superior to the recent advanced methods in the few-shot scenario where only a few samples are used for training.