SSRIS
发表于 2025-3-30 11:07:57
S. T. Arnold,J. H. Hendricks,K. H. Bowent event types, which could further boost the performance of event extraction. Experimental results on two widely used event extraction datasets demonstrate that our method could improve the original cascade decoding framework by up to 2.2 percentage points of F1 score and outperform a number of competitive baseline methods.
MOTIF
发表于 2025-3-30 14:19:30
Improving Cascade Decoding with Syntax-Aware Aggregator and Contrastive Learning for Event Extractiot event types, which could further boost the performance of event extraction. Experimental results on two widely used event extraction datasets demonstrate that our method could improve the original cascade decoding framework by up to 2.2 percentage points of F1 score and outperform a number of competitive baseline methods.
尊严
发表于 2025-3-30 20:22:07
0302-9743 nguage Resource and Evaluation, Pre-trained Language Models, Social Computing and Sentiment Analysis, NLP Applications.. 978-981-99-6206-8978-981-99-6207-5Series ISSN 0302-9743 Series E-ISSN 1611-3349
Root494
发表于 2025-3-30 23:52:33
http://reply.papertrans.cn/23/2258/225765/225765_54.png