Aligning Script Events with Narrative Texts

Aligning Script Events with Narrative Texts Simon Ostermann† Michael Roth†‡ Stefan Thater† Manfred Pinkal† † Saarland University ‡ University of Illinois at Urbana-Champaign {simono|mroth|stth|pinkal}@coli.uni-saarland.de Abstract Script knowledge plays a central role in text understanding and is relevant for a va- riety of downstream tasks. In this paper, we consider two recent datasets which provide a rich and general representation of script events in terms of paraphrase sets. We in- troduce the task of mapping event mentions in narrative texts to such script event types, and present a model for this task that ex- ploits rich linguistic representations as well as information on temporal ordering. The results of our experiments demonstrate that this complex task is indeed feasible. 1 Introduction Event structure is a prominent topic in NLP. While semantic role labelers (Gildea and Jurafsky, 2002; Palmer et al., 2010) are well-established tools for the analysis of the internal structure of event de- scriptions, modeling relations between events has gained increasing attention in recent years. Re- search on event coreference (Bejan and Harabagiu, 2010; Lee et al., 2012), temporal event ordering in newswire texts (Ling and Weld, 2010), as well as shared tasks on cross-document event ordering (Minard et al., 2015, inter alia) have in common that they model cross-document relations. The focus of this paper is on the task of analyzing text-internal event structure. We share the view of a long tradition in NLP (see e.g. Schank and Abelson (1975); Chambers and Jurafsky (2009); Regneri et al. (2010)) that script knowledge is of central im- portance to this task, i.e. common-sense knowledge about events and their typical order in everyday activities (also referred to as scenarios, Barr and Feigenbaum (1981)). Script knowledge guides ex- pectation by predicting which type of event or dis- course referent might be addressed next in a story (Modi et al., 2017), allows to infer missing events from events explicitly mentioned (Chambers and Jurafsky, 2009; Jans et al., 2012; Rudinger et al., 2015), and to determine text-internal temporal or- der (Modi and Titov, 2014; Frermann et al., 2014). We address the task of automatically mapping narrative texts to scripts, which will leverage ex- plicit script knowledge for the afore-mentioned as- pects of text understanding, as well as for down- stream tasks such as textual entailment, question answering or paraphrase detection. We build on the work of Regneri et al. (2010) and Wanzare et al. (2016), who collect explicit script knowledge via crowdsourcing, by asking people to describe ev- eryday activities. These crowdsourced descriptions form a basis for high-quality automatic extraction of script structure without any human intervention (Regneri et al., 2010; Wanzare et al., 2017). The events of the resulting structure are defined as sets of alternative realizations, which cover lexical vari- ation and provide paraphrase information. To the best of our knowledge, these advantages have not been explicitly used elsewhere. Aligning script structures with texts is a complex task. In a first attempt, we assume that three steps are necessary to solve it, although in …

Content truncated to 500 words