Relation Extraction with Self-determined Graph Convolutional Network
This addresses the problem of non-end-to-end processing in relation extraction for NLP researchers, offering an incremental improvement by replacing linguistic tools with self-attention.
The paper tackles relation extraction by proposing a Self-determined Graph Convolutional Network (SGCN) that uses self-attention to build graphs without linguistic tools, achieving state-of-the-art results on the TACRED dataset and outperforming traditional GCN methods.
Relation Extraction is a way of obtaining the semantic relationship between entities in text. The state-of-the-art methods use linguistic tools to build a graph for the text in which the entities appear and then a Graph Convolutional Network (GCN) is employed to encode the pre-built graphs. Although their performance is promising, the reliance on linguistic tools results in a non end-to-end process. In this work, we propose a novel model, the Self-determined Graph Convolutional Network (SGCN), which determines a weighted graph using a self-attention mechanism, rather using any linguistic tool. Then, the self-determined graph is encoded using a GCN. We test our model on the TACRED dataset and achieve the state-of-the-art result. Our experiments show that SGCN outperforms the traditional GCN, which uses dependency parsing tools to build the graph.