LFDe: A Lighter, Faster and More Data-Efficient Pre-training Framework for Event Extraction
Pre-training Event Extraction (EE) models on unlabeled data is an effective strategy that
frees researchers from costly and labor-intensive data annotation. However, existing pre …
frees researchers from costly and labor-intensive data annotation. However, existing pre …
Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm
Document-level event extraction aims to extract structured event information from
unstructured text. However, a single document often contains limited event information and …
unstructured text. However, a single document often contains limited event information and …
CMNEE: A Large-Scale Document-Level Event Extraction Dataset based on Open-Source Chinese Military News
Extracting structured event knowledge, including event triggers and corresponding
arguments, from military texts is fundamental to many applications, such as intelligence …
arguments, from military texts is fundamental to many applications, such as intelligence …
Scented-EAE: Stage-Customized Entity Type Embedding for Event Argument Extraction
Y Yang, J Guo, K Shuang, C Mao - Findings of the Association for …, 2024 - aclanthology.org
Existing methods for incorporating entities into EAE rely on prompts or NER. They typically
fail to explicitly explore the role of entity types, which results in shallow argument …
fail to explicitly explore the role of entity types, which results in shallow argument …
Word-level Commonsense Knowledge Selection for Event Detection
S Yang, Y Hong, S He, Q Xu, J Yao - Proceedings of the 2024 …, 2024 - aclanthology.org
Event Detection (ED) is a task of automatically extracting multi-class trigger words. The
understanding of word sense is crucial for ED. In this paper, we utilize context-specific …
understanding of word sense is crucial for ED. In this paper, we utilize context-specific …