Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation
| Autor: | David Wilmot, Frank Keller |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science media_common.quotation_subject Representation (arts) computer.software_genre Measure (mathematics) 050105 experimental psychology Machine Learning (cs.LG) 03 medical and health sciences 0302 clinical medicine 0501 psychology and cognitive sciences Narrative Uncertainty reduction theory media_common Computer Science - Computation and Language business.industry 05 social sciences Surprise Language model Artificial intelligence business Computation and Language (cs.CL) computer 030217 neurology & neurosurgery Natural language processing |
| Zdroj: | Wilmot, D & Keller, F 2020, Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation . in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics . Online, pp. 1763-1788, 2020 Annual Conference of the Association for Computational Linguistics, Virtual conference, Washington, United States, 5/07/20 . < https://www.aclweb.org/anthology/2020.acl-main.161 > |
| DOI: | 10.18653/v1/2020.acl-main.161 |
| Popis: | Suspense is a crucial ingredient of narrative fiction, engaging readers and making stories compelling. While there is a vast theoretical literature on suspense, it is computationally not well understood. We compare two ways for modelling suspense: surprise, a backward-looking measure of how unexpected the current state is given the story so far; and uncertainty reduction, a forward-looking measure of how unexpected the continuation of the story is. Both can be computed either directly over story representations or over their probability distributions. We propose a hierarchical language model that encodes stories and computes surprise and uncertainty reduction. Evaluating against short stories annotated with human suspense judgements, we find that uncertainty reduction over representations is the best predictor, resulting in near-human accuracy. We also show that uncertainty reduction can be used to predict suspenseful events in movie synopses. 9 pages, 3 figures, accepted as long paper to ACL 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|