FA-RCNet: A Fused Feature Attention Network for Relationship Classification

Abstract

Relation extraction is an important task in natural language processing. It plays an integral role in intelligent question-and-answer systems, semantic search, and knowledge graph work. For this task, previous studies have demonstrated the effectiveness of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory networks (LSTMs) in relational classification tasks. Recently, due to the superior performance of the pre-trained model BERT, BERT has become a feature extraction module for many relational classification models, and good results have been achieved in work related to BERT. However, most of such work uses the deepest levels of features. The important role of shallow-level information in the relational classification task is ignored. Based on the above problems, a relationship classification network FA-RCNet (fusion-attention relationship classification network) with feature fusion and attention mechanism is proposed in this paper. FA-RCNet fuses shallow-level features with deep-level features, and augments entity features and global features by the attention module so that the feature vector can perform the relational classification task more perfectly. In addition, the model in this paper achieves advanced results on both the SemEval-2010 Task 8 dataset and the KBP37 dataset compared to previously published models.

“Standard Text” Relational Classification Model Based on Concatenated Word Vector Attention and Feature Concatenation

“…Compared with the BiLSTM-attention and multi-attention CNN based on bidirectional long-short-term memory network and attention mechanism, it increased by 3.7% and 2.7%, respectively. Compared with CRSAtt [37] and FA-RCNet [38] based on the BERT pre-trained model, it increased by 0.8% and 0.9%, respectively. The experimental results on the emEval-2010 Task 8 dataset showed that the relationship classification model proposed in this paper also achieved good results on the SemEval-2010 Task 8 dataset.…”