Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 808–817, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings Deyu Zhou† Xuan Zhang† Yulan He§ † School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, China § School of Engineering and Applied Science, Aston University, UK {d.zhou, xuanzhang}@seu.edu.cn, y.he@cantab.net Abstract To extract structured representations of newsworthy events from Twitter, unsuper- vised models typically assume that tweets involving the same named entities and ex- pressed using similar words are likely to belong to the same event. Hence, they group tweets into clusters based on the co- occurrence patterns of named entities and topical keywords. However, there are two main limitations. First, they require the number of events to be known beforehand, which is not realistic in practical applica- tions. Second, they don’t recognise that the same named entity might be referred to by multiple mentions and tweets us- ing different mentions would be wrongly assigned to different events. To over- come these limitations, we propose a non- parametric Bayesian mixture model with word embeddings for event extraction, in which the number of events can be in- ferred automatically and the issue of lex- ical variations for the same named entity can be dealt with properly. Our model has been evaluated on three datasets with sizes ranging between 2,499 and over 60 million tweets. Experimental results show that our model outperforms the baseline approach on all datasets by 5-8% in F-measure. 1 Introduction Event extraction from texts is to automatically ex- tract key information of events such as what hap- pened to whom, when and where. Previous re- search mainly focused on news articles, the best and abundant source of newsworthy events. With the increasing popularity of social media plat- forms, events are also reported and discussed in Table 1: An example of several tweets describ- ing the same event about “Space shuttle Atlantis landed at Kennedy Space Center in Florida on 2011/07/08’’. Boom! #shuttle #Atlantis is back! The shuttle is down, welcome back Atlantis, goodbye shuttle program. Atlantis lands safely in Florida, marking the end of NASA’s 30-yr space shuttle pro- gramme. Space shuttle Atlantis lands at Kennedy space center, ending NASA’s 30-year shuttle pro- gram. social media apart from news articles. It was re- ported in (Petrovic et al., 2013) that even 1% of public Twitter stream covers 95% of all events on newswire. Extracting events from social me- dia makes it possible to quickly understand what is being discussed. It can be further integrated into downstream applications such as tracking the public’s viewpoints towards a certain event. How- ever, due to the difficulty in acquiring annotated data for training and the short and informal text commonly appeared in social media, traditional approaches (Grishman et al., 2005; Tanev et al., 2008; Piskorski et al., 2008) to …

Content truncated to 500 words