Literary Style

Style has often been understood both too broadly and too narrowly. In consequence, it has not defined a psychologically coherent area of study. In this chapter, Hogan first defines style so as to make possible a consistent and systematic theoretical account of the topic in relation to cognitive and affective science. This definition stresses that style varies by both scope and level—thus, the range of text or texts that may share a style (from a single passage to a historical period) and the components of a work that might involve a shared style (including story, narration, and verbalization). This chapter also addresses a second question—what purposes are served by style? There are three key functions of style: 1) the shaping of story understanding, 2) the communication of thematic concerns (i.e., concerns that extend beyond the work to values in the world), and 3) the arousal and modulation of emotion. Hogan illustrates the main points of this chapter by reference to literary works, prominently Woolf’s Mrs. Dalloway.

Explainable Inference on Sequential Data via Memory-Tracking

In this paper we present a novel mechanism to get explanations that allow to better understand network predictions when dealing with sequential data. Specifically, we adopt memory-based networks — Differential Neural Computers — to exploit their capability of storing data in memory and reusing it for inference. By tracking both the memory access at prediction time, and the information stored by the network at each step of the input sequence, we can retrieve the most relevant input steps associated to each prediction. We validate our approach (1) on a modified T-maze, which is a non-Markovian discrete control task evaluating an algorithm’s ability to correlate events far apart in history, and (2) on the Story Cloze Test, which is a commonsense reasoning framework for evaluating story understanding that requires a system to choose the correct ending to a four-sentence story. Our results show that we are able to explain agent’s decisions in (1) and to reconstruct the most relevant sentences used by the network to select the story ending in (2). Additionally, we show not only that by removing those sentences the network prediction changes, but also that the same are sufficient to reproduce the inference.