Event Linking: Grounding Event Mentions to Wikipedia

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2679–2688 May 2-6, 2023 ©2023 Association for Computational Linguistics Event Linking: Grounding Event Mentions to Wikipedia Xiaodong Yu1 Wenpeng Yin2 Nitish Gupta3 Dan Roth1 1University of Pennsylvania 2Penn State University 3Google Research {xdyu, danroth}@seas.upenn.edu wenpeng@psu.edu gnnitish@gmail.com Abstract Comprehending an article requires understand- ing its constituent events. However, the context where an event is mentioned often lacks the de- tails of this event. A question arises: how can the reader obtain more knowledge about this particular event in addition to what is provided by the local context in the article? This work defines Event Linking, a new natural language understanding task at the event level. Event linking tries to link an event mention appearing in an article to the most appropri- ate Wikipedia page. This page is expected to provide rich knowledge about what the event mention refers to. To standardize the research in this new direction, we contribute in four- fold. First, this is the first work in the com- munity that formally defines the Event Link- ing task. Second, we collect a dataset for this new task. Specifically, we automatically gather the training set from Wikipedia, and then create two evaluation sets: one from the Wikipedia domain, reporting the in-domain performance, and a second from the real-world news do- main, to evaluate out-of-domain performance. Third, we retrain and evaluate two state-of-the- art (SOTA) entity linking models, showing the challenges of event linking, and we propose an event-specific linking system, EVELINK, to set a competitive result for the new task. Fourth, we conduct a detailed and insightful analysis to help understand the task and the limitations of the current model. Overall, as our analy- sis shows, Event Linking is a challenging and essential task requiring more effort from the community. 1 1 Introduction Grounding is a process of disambiguation and knowledge acquisition, and is an important task for natural language understanding. Entity linking, grounding entity mentions to a knowledge base 1Data and code are available here: http://cogcomp. org/page/publication_view/996. Two homemade pressure cooker bombs detonated in Boston, killing 3 people and injuring hundreds of others. The police released the images of two suspects. Boston Boston, officially the City of Boston, is the capital and most populous city of the Commonwealth of Massachusetts in the United States ...... Boston Marathon Bombing The Boston Marathon bombing was a domestic terrorist attack that took place during the annual Boston Marathon on April 15, 2013. ...... Wikipedia Local context Figure 1: Examples of Event linking and Entity linking. The left side is the local context, and the right side con- tains Wikipedia pages. Entity linking model connects the entity “Boston” to the Wikipedia page “Boston”, while event linking model links the event “detonated” to the Wikipedia page “Boston Marathon Bombing”, which is more relevant to the local context. (usually Wikipedia) (Bunescu and Pasca, 2006; Mi- halcea and Csomai, 2007; Ratinov et al., 2011; Gupta et al., 2017; Wu et …

Content truncated to 500 words