Effective Use of Graph Convolution Network and Contextual Sub-Tree forCommodity News Event Extraction
This work addresses a less researched problem in commodity news for applications like price prediction, but it is incremental as it adapts existing methods to a specific domain.
The paper tackled event extraction from commodity news, which is challenging due to unique characteristics, by proposing a method using Graph Convolutional Networks with a contextual sub-tree and a domain-adapted BERT model, achieving an F1 score of 0.90 and outperforming other models by up to 23% in argument roles classification.
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 abroad range of applications such as under-standing 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 ex-traction in commodity news. The event ex-traction model is trained using feature embed-dings 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 out-performs 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 re-producibility, the code and trained models are made publicly available1.