ملف الباحث

Dadong Wan

ورقة واحدة في مجموعة PaperMetrix

المنشورات

أوراق هذا المؤلف

  1. Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction

    2018 · arXiv (Cornell University)

    Attention mechanisms are often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention models are insufficient for the learning of different contexts …