Modeling Event Salience in Narratives via Barthes’ Cardinal Functions

Proceedings of the 28th International Conference on Computational Linguistics, pages 1784–1794 Barcelona, Spain (Online), December 8-13, 2020 1784 Modeling Event Salience in Narratives via Barthes’ Cardinal Functions Takaki Otake1 Sho Yokoi1,2 Naoya Inoue1,2 ∗ Ryo Takahashi1,2 Tatsuki Kuribayashi1,3 Kentaro Inui1,2 1Tohoku University 2RIKEN 3Langsmith Inc. {takaki, yokoi, ryo.t, kuribayashi, inui}@ecei.tohoku.ac.jp naoya.inoue.lab@gmail.com Abstract Events in a narrative differ in salience: some are more important to the story than others. Esti- mating event salience is useful for tasks such as story generation, and as a tool for text analysis in narratology and folkloristics. To compute event salience without any annotations, we adopt Barthes’ definition of event salience and propose several unsupervised methods that require only a pre-trained language model. Evaluating the proposed methods on folktales with event salience annotation, we show that the proposed methods outperform baseline methods and find fine-tuning a language model on narrative texts is a key factor in improving the proposed methods. 1 Introduction Narratives (e.g., folktales, literary short stories) are the representations of a series of events (Abbott, 2008). Events, the essential components of narratives, differ in salience: some are more important to the story than others. Taking Cinderella as an example, The prince falls in love with Cinderella is a salient event; however, Cinderella draws water from a well is not. Estimating event salience is a fundamental task in analyzing and processing narratives, ranging from narrative analysis to automatic story generation (Ouyang and McKeown, 2015; Choubey et al., 2018; Papalampidi et al., 2019). This study aims to estimate event salience in an unsupervised manner. Manually annotating event salience is prohibitively costly because it requires annotators to deeply understand the notion of event salience in narratology (Finlayson, 2015). In fact, despite a long history of research, very few narrative corpora are annotated with event salience. Thus, it is crucial to develop a method for estimating event salience that does not rely on event salience-annotated corpora. In order to estimate event salience without annotated data, we adopt the definition of cardinal functions (CFs) introduced by Barthes (1966; 1975), the successor of Proppian function 1 (Propp, 1928), as follows: cardinal functions are logically essential to the narrative action and cannot be eliminated without destroying its causal-chronological coherence. (Prince, 2003) This definition suggests a simple test for identifying event salience: an event is highly salient if removing it greatly reduces the story’s coherence. We adopt this idea for two reasons. First, CFs are commonly used in narrative analysis (Abbott, 2008). Second, the idea of CFs can be directly operationalized without any annotated data. Computing event salience based on the idea of CFs requires measuring narrative texts’ coherence, but recent advances in discourse coherence models can provide a solution for this difficulty. To date, a wide variety of discourse coherence models have been proposed (Barzilay and Lapata, 2008; Li and Jurafsky, 2017). See et al. (2019) have reported that GPT-2 (Radford et al., 2019), a powerful left-to-right language model (LM), could accurately estimate narrative texts’ coherence, importantly, without any annotated data. …

Content truncated to 500 words