Effective Use of Graph Convolution Network and Contextual Sub-Tree for Commodity News Event Extraction

Abstract

Event extraction in commodity news is a less researched area as compared to generic event extraction. However, accurate event extraction from commodity news is useful in a broad range of applications such as understanding event chains and learning event-event relations, which can then be used for commodity price prediction. The events found in commodity news exhibit characteristics different from generic events, hence posing a unique challenge in event extraction using existing methods. This paper proposes an effective use of Graph Convolutional Networks (GCN) with a pruned dependency parse tree, termed contextual sub-tree, for better event extraction in commodity news. The event extraction model is trained using feature embeddings from ComBERT, a BERT-based masked language model that was produced through domain-adaptive pre-training on a commodity news corpus. Experimental results show the efficiency of the proposed solution, which outperforms existing methods with F1 scores as high as 0.90. Furthermore, our pre-trained language model outperforms GloVe by 23%, and BERT and RoBERTa by 7% in terms of argument roles classification. For the goal of reproducibility, the code and trained models are made publicly available.