Enhancing entity and relation extraction with dynamic hard negative augmentation framework

Entity and relation extraction, a fundamental task in information extraction, plays a crucial role in modeling unstructured text by identifying meaningful entities and their semantic relationships. While existing methods have shown effectiveness, they still face challenges in accurately identifying entity boundaries and extracting complex relationships. These challenges primarily arise from current contrastive learning approaches, which uniformly handle all negative samples in boundary detection and relation extraction without emphasizing the learning of hard negative samples. Additionally, the scarcity of hard negative samples limits the exploration of the state space near the anchors. To tackle these challenges, we introduce Dynamic Hard Negative Augmentation, an innovative framework designed to strategically explore and generate hard negative samples, thereby enhancing the learning of challenging cases through adaptive contrastive learning. During the negative sample augmentation process, we employ adversarial training to explore underrepresented areas of hard negative samples, generating a comprehensive coverage of the hard negative sample space to effectively explore the state space. We further introduce a dynamic enhancement mechanism that continuously optimizes the proportion of hard negative samples during training, ensuring targeted learning of these challenging cases.

Authors

• Qibin Li Dalian University of Technology
• Shengyuan Bai International Digital Economy Academy, Dalian University of Technology
• Nai Zhou Quan Cheng Laboratory
• Nianmin Yao Dalian University of Technology

Keywords

• Entity and relation extraction
• Hard negative
• Dynamic enhancement