Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network
This addresses the problem of extracting complex semantic relationships across sentences in documents for domains like biochemistry, though it is incremental as it builds on existing graph-based methods.
The paper tackles inter-sentence relation extraction by proposing a document-level graph convolutional neural network model that captures local and non-local dependencies, achieving comparable performance to state-of-the-art neural models on two biochemistry datasets.
Inter-sentence relation extraction deals with a number of complex semantic relationships in documents, which require local, non-local, syntactic and semantic dependencies. Existing methods do not fully exploit such dependencies. We present a novel inter-sentence relation extraction model that builds a labelled edge graph convolutional neural network model on a document-level graph. The graph is constructed using various inter- and intra-sentence dependencies to capture local and non-local dependency information. In order to predict the relation of an entity pair, we utilise multi-instance learning with bi-affine pairwise scoring. Experimental results show that our model achieves comparable performance to the state-of-the-art neural models on two biochemistry datasets. Our analysis shows that all the types in the graph are effective for inter-sentence relation extraction.