Open Event Extraction from Online Text using a Generative Adversarial Network

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 282–291, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 282 Open Event Extraction from Online Text using a Generative Adversarial Network Rui Wang† Deyu Zhou†∗ Yulan He§ †School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, China §Department of Computer Science, University of Warwick, UK {rui wang, d.zhou}@seu.edu.cn, yulan.he@warwick.ac.uk Abstract To extract the structured representations of open-domain events, Bayesian graphical mod- els have made some progress. However, these approaches typically assume that all words in a document are generated from a single event. While this may be true for short text such as tweets, such an assumption does not generally hold for long text such as news articles. More- over, Bayesian graphical models often rely on Gibbs sampling for parameter inference which may take long time to converge. To address these limitations, we propose an event extrac- tion model based on Generative Adversarial Nets, called Adversarial-neural Event Model (AEM). AEM models an event with a Dirich- let prior and uses a generator network to cap- ture the patterns underlying latent events. A discriminator is used to distinguish documents reconstructed from the latent events and the original documents. A byproduct of the dis- criminator is that the features generated by the learned discriminator network allow the visu- alization of the extracted events. Our model has been evaluated on two Twitter datasets and a news article dataset. Experimental results show that our model outperforms the baseline approaches on all the datasets, with more sig- nificant improvements observed on the news article dataset where an increase of 15% is ob- served in F-measure. 1 Introduction With the increasing popularity of the Internet, online texts provided by social media platform (e.g. Twitter) and news media sites (e.g. Google news) have become important sources of real- world events. Therefore, it is crucial to automati- cally extract events from online texts. Due to the high variety of events discussed on- line and the difficulty in obtaining annotated data ∗corresponding author for training, traditional template-based or super- vised learning approaches for event extraction are no longer applicable in dealing with online texts. Nevertheless, newsworthy events are often dis- cussed by many tweets or online news articles. Therefore, the same event could be mentioned by a high volume of redundant tweets or news arti- cles. This property inspires the research commu- nity to devise clustering-based models (Popescu et al., 2011; Abdelhaq et al., 2013; Xia et al., 2015) to discover new or previously unidentified events without extracting structured representations. To extract structured representations of events such as who did what, when, where and why, Bayesian approaches have made some progress. Assuming that each document is assigned to a sin- gle event, which is modeled as a joint distribu- tion over the named entities, the date and the loca- tion of the event, …

Content truncated to 500 words