Language Model Priming for Cross-Lingual Event Extraction

Abstract: We present a novel, language-agnostic approach to "priming" LLMs for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the input to the transformer stack's LLM differently depending on the question(s) being asked of the model at runtime. For instance, if the model is being asked to identify arguments for the trigger "protested", we will provide that trigger as part of the input to the LLM, allowing it to produce different representations for candidate arguments than when it is asked about arguments for the trigger "arrest" elsewhere in the same sentence. We show that by enabling the LLM to better compensate for the deficits of sparse and noisy training data, our approach improves both trigger and argument detection and classification significantly over the state of the art in a zero-shot cross-lingual setting.