Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction

Proceedings of the 28th International Conference on Computational Linguistics, pages 6424–6435 Barcelona, Spain (Online), December 8-13, 2020 6424 Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction Angrosh Mandya, Danushka Bollegala∗and Frans Coenen Department of Computer Science, University of Liverpool, UK {angrosh,danushka.bollegala,coenen}@liverpool.ac.uk Abstract We propose in this paper a contextualised graph convolution network over multiple dependency sub-graphs for relation extraction. A novel method to construct multiple sub-graphs using words in shortest dependency path and words linked to entities in the dependency graph is proposed. Graph convolution operation is performed over the resulting multiple sub-graphs to obtain more informative features useful for relation extraction. Our experimental results show that the pro- posed method achieves superior performance over existing GCN-based models achieving state- of-the-art performance on cross-sentence n-ary relation extraction and SemEval 2010 Task 8 sentence-level relation extraction task. Our model also achieves a comparable performance to the SoTA on the TACRED dataset. 1 Introduction In recent times, Graph Convolutional Network (GCN) (Kipf and Welling, 2016) based models such as Contextualised GCN (C-GCN) (Zhang et al., 2018) and Attention Guided GCN (AGGCN) (Guo et al., 2019) are shown to be useful for relation extraction. The C-GCN model employs pruned dependency trees obtained using a path-centric pruning distance to filter irrelevant nodes from sentence graph to aid in relation extraction. Experiments with C-GCN model shows that the performance of the C-GCN model significantly decreases with the inclusion of all nodes in the sentence graph obtained from the dependency graph (Zhang et al., 2018), thus making it important to use a right pruning distance to achieve optimum performance. The AGGCN model (Guo et al., 2019) on the other hand, instead of using pruned dependency trees, considers the full dependency tree with a self-attention mechanism to learn node representation useful for relation extraction. In contrast to these GCN-based models using a single graph, we propose in this paper to use multiple sub-graphs constructed from dependency tree to represent a sentence for relation extraction. Given the decrease in performance of C-GCN with an increase in the size of graph (Zhang et al., 2018), we hypothesise that using multiple sub-graphs in place of a single graph can boost performance of GCN-based models for relation extraction. In comparison to the AGGCN model (Guo et al., 2019), our proposed model simply considers smaller graphs associated with entities to learn representation for important nodes in the sentence. Further, while the pruning strategy used by the C-GCN model (Zhang et al., 2018) is applicable for sentence-level relation extraction, it is not suitable for cross-sentence n-ary relation extraction as there could be more than two entities across multiple sentences. The challenges arise in obtaining a single dependency path in the LCA sub-tree connecting n-ary entities across sentences for cross-sentence rela- tion extraction. Previous work on cross-sentence relation extraction task (Peng et al., 2017; Song et al., 2018; Guo et al., 2019) have largely made use of full dependency graph with additional features such as adjacent words and co-reference links (Peng et al., …

Content truncated to 500 words