Analogous Process Structure Induction for Sub-event Sequence Prediction

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 1541–1550, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 1541 Analogous Process Structure Induction for Sub-event Sequence Prediction Hongming Zhang1∗, Muhao Chen2, Haoyu Wang2, Yangqiu Song1, & Dan Roth2 1Department of Computer Science and Engineering, HKUST 2Department of Computer and Information Science, UPenn {hzhangal, yqsong}@cse.ust.hk {why16gzl, muhao, danroth}@seas.upenn.edu Abstract Computational and cognitive studies of event understanding suggest that identifying, com- prehending, and predicting events depend on having structured representations of a se- quence of events and on conceptualizing (ab- stracting) its components into (soft) event cat- egories. Thus, knowledge about a known pro- cess such as “buying a car” can be used in the context of a new but analogous process such as “buying a house”. Nevertheless, most event understanding work in NLP is still at the ground level and does not consider abstrac- tion. In this paper, we propose an Analogous Process Structure Induction (APSI) frame- work, which leverages analogies among pro- cesses and conceptualization of sub-event in- stances to predict the whole sub-event se- quence of previously unseen open-domain processes. As our experiments and analy- sis indicate, APSI1 supports the generation of meaningful sub-event sequences for unseen processes and can help predict missing events. 1 Introduction Understanding events has long been a challeng- ing task in NLP, to which many efforts have been devoted by the community. However, most exist- ing works are focusing on procedural (or horizon- tal) event prediction tasks. Examples include pre- dicting the next event given an observed event se- quence (Radinsky et al., 2012) and identifying the effect of a biological process (i.e., a sequence of events) on involved entities (Berant et al., 2014). These tasks mostly focus on predicting related events in a procedure based on their statistical cor- relations in previously observed text. As a re- sult, understanding the meaning of an event might ∗ This work was done when the first author was visiting the University of Pennsylvania. 1Code is available at: http://cogcomp.org/ page/publication_view/910. Figure 1: An illustration of leveraging known processes to predict the sub-event sequence of a new process. not be crucial for these horizontal tasks. For ex- ample, simply selecting the most frequently co- occurring event can offer acceptable performance on the event prediction task (Granroth-Wilding and Clark, 2016). Computational and cognitive studies (Schank and Abelson, 1977; Zacks and Tversky, 2001) suggest that inducing and utilizing the hierarchical structure2 of events is a crucial component of how humans understand new events and can help many aforementioned horizontal event prediction tasks. Consider the example in Figure 1. Assume that one has never bought a house, but is familiar with how to “buy a car” and “rent a house”; referring to analogous steps in these two relevant processes would still provide guidance for the target process of “buy a house”. Motivated by this hypothesis, our work proposes to directly evaluate a model’s event understanding ability. We define this as the 2The original paper refers to the …

Content truncated to 500 words