Distinguishing Past, On-going, and Future Events: The EventStatus Corpus

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 44–54, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Distinguishing Past, On-going, and Future Events: The EventStatus Corpus Ruihong Huang Texas A&M University huangrh@cse.tamu.edu Ignacio Cases Stanford University cases@stanford.edu Dan Jurafsky Stanford University jurafsky@stanford.edu Cleo Condoravdi Stanford University cleoc@stanford.edu Ellen Riloff University of Utah riloff@cs.utah.edu Abstract Determining whether a major societal event has already happened, is still on-going, or may occur in the future is crucial for event pre- diction, timeline generation, and news sum- marization. We introduce a new task and a new corpus, EventStatus, which has 4500 En- glish and Spanish articles about civil unrest events labeled as PAST, ON-GOING, or FU- TURE. We show that the temporal status of these events is difficult to classify because lo- cal tense and aspect cues are often lacking, time expressions are insufficient, and the lin- guistic contexts have rich semantic composi- tionality. We explore two approaches for event status classification: (1) a feature-based SVM classifier augmented with a novel induced lex- icon of future-oriented verbs, such as “threat- ened” and “planned”, and (2) a convolutional neural net. Both types of classifiers improve event status recognition over a state-of-the-art TempEval model, and our analysis offers lin- guistic insights into the semantic composition- ality challenges for this new task. 1 Introduction When a major societal event is mentioned in the news (e.g., civil unrest, terrorism, natural disaster), it is important to understand whether the event has al- ready happened (PAST), is currently happening (ON- GOING), or may happen in the future (FUTURE). We introduce a new task and corpus for studying the temporal/aspectual properties of major events. The EventStatus corpus consists of 4500 English and Spanish news articles about civil unrest events, such as protests, demonstrations, marches, and strikes, in which each event is annotated as PAST, ON-GOING, or FUTURE (sublabeled as PLANNED, ALERT or POSSIBLE). This task bridges event extraction re- search and temporal research in the tradition of TIMEBANK (Pustejovsky et al., 2003) and TempE- val (Verhagen et al., 2007; Verhagen et al., 2010; UzZaman et al., 2013). Previous corpora have be- gun this association: TIMEBANK, for example, in- cludes temporal relations linking events with Doc- ument Creation Times (DCT). But the EventStatus task and corpus offers several new research direc- tions. First, major societal events are often discussed be- fore they happen, or while they are still happening, because they have the potential to impact a large number of people. News outlets frequently report on impending natural disasters (e.g., hurricanes), an- ticipated disease outbreaks (e.g., Zika virus), threats of terrorism, and plans or warnings of potential civil unrest (e.g., strikes and protests). Traditional event extraction research has focused primarily on recog- nizing events that have already happened. Further- more, the linguistic contexts of on-going and future events involve complex compositionality, and fea- tures like explicit time expressions are less useful. Our results demonstrate that a state-of-the-art Tem- pEval system has difficulty identifying on-going and …

Content truncated to 500 words