Relation Extraction via Attention-Based CNNs using Token-Level Representations
Yan Wang, Xin Xin, Ping Guo · 2019
Relation extraction is an important task in the field of natural language processing (NLP). Most existing methods usually utilize word-level representations, ignoring massive information from the texts. To address this issue, we utilize BERT to pretrain token-level bidirectional contextual representations from raw sentences, then employ a Transformer encoder to train token-level representations mentioned above again. To capture the most important information of the sentences, we employ a convolutional neural network (CNN) with entity-aware attention to extract high-level features from these token-level representations of the sentences. On the SemEval-2010 Task 8 dataset, our model achieves 87.8% F1-score and outperforms several previous models without rich prior knowledge.