Event-argument extraction is a challenging task, particularly in Arabic due to sparse
linguistic resources. To fill this gap, we introduce the\hadath corpus ($550 $ k tokens) as an …

Traditional event detection methods require predefined event schemas. However, manually
defining event schemas is expensive and the coverage of schemas is limited. To this end …

Translating training data into target languages has proven beneficial for cross-lingual
transfer. However, for structure extraction tasks, translating data requires a label projection …

Generative information extraction (Generative IE) aims to generate structured text
sequences from unstructured text using a generative framework. Scaling in model size …

Document-level Event Argument Extraction (DEAE) aims to extract structural event
knowledge composed of arguments and roles beyond the sentence level. Existing methods …

Many real-world applications require making multiple predictions from the same text. Fine-
tuning a large pre-trained language model for each downstream task causes computational …

Event extraction is an important part of natural language information extraction, and it's
widely employed in other natural language processing tasks including question answering …

Zero-shot Cross-lingual EAE has garnered significant interests from the community because
it could minimize the need for extensive data annotation to identify the roles of the …

Event argument extraction (EAE) identifies the arguments and their roles from a piece of text
under a given event. Existing methods for EAE mostly rely on generation models and use …

Large language models (LLMs) have made significant strides in various natural language
processing tasks, yet cross-domain event argument extraction remains a complex challenge …