Abstract
Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Previous methods for EE typically model it as a classification task, which are usually prone to the data scarcity problem. In this paper, we propose a new learning paradigm of EE, by explicitly casting it as a machine reading comprehension problem (MRC). Our approach includes an unsupervised question generation process, which can transfer event schema into a set of natural questions, followed by a BERT-based question-answering process to retrieve answers as EE results. This learning paradigm enables us to strengthen the reasoning process of EE, by introducing sophisticated models in MRC, and relieve the data scarcity problem, by introducing the large-scale datasets in MRC. The empirical results show that: i) our approach attains state-of-the-art performance by considerable margins over previous methods. ii) Our model is excelled in the data-scarce scenario, for example, obtaining 49.8\% in F1 for event argument extraction with only 1\% data, compared with 2.2\% of the previous method. iii) Our model also fits with zero-shot scenarios, achieving $37.0\%$ and $16\%$ in F1 on two datasets without using any EE training data.
Highlights
Event extraction (EE), a crucial information extraction (IE) task, aims to extract event information in texts
2) Especially, RCEE ER outperforms BERTEE with over 5% in argument extraction, which indicates that the improvements are mainly from problem reformulation, rather than introducing BERT representations
3) The high recall of RCEE ER indicates that it can predict more examples than baselines, which may imply that RCEE ER can tackle difficult cases that fail baseline models
Summary
Event extraction (EE), a crucial information extraction (IE) task, aims to extract event information in texts. Classification based methods are data-hungry, which require a great deal of training data to ensure good performance (Chen et al, 2017; Li et al, 2013; Liu et al, 2018a). Such methods generally cannot deal with new event types never encountered during training time (Huang et al, 2018)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have