PSED: A Dataset for Selecting Emphasis in Presentation Slides

Abstract

Emphasizing words in presentation slides allows viewers to direct their gaze to focal points without reading the entire slide, retaining their attention on the speaker. Despite many studies on automatic slide generation, few have addressed helping authors choose which words to emphasize. Motivated by this, we study the problem of choosing candidates for emphasis by introducing a new dataset containing presentation slides with a wide variety of topics. We evaluated a range of state-of-the-art models on this novel dataset by organizing a shared task and inviting multiple researchers to model emphasis in slides.

Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualized Embeddings

“…The annotation scheme and the emphasis probability calculation has been shown with an example in Table 3. More information about the task and data creation can be found in Shirani et al (2021).…”

“…Emphasis Selection for written text in visual media from crowdsourced label distributions was first proposed by Shirani et al (2019) and then by Shirani et al (2020a) in SemEval-2020 Task 10, Emphasis Selection for Written Text in Visual Media (Shirani et al 2020b). AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides (Shirani et al 2021) builds on the same SemEval-2020 Task 10. Presentation slides have become quite common in workplace scenarios and researchers have previously developed resources that guide presenters on the aspects of overall style, color, and font sizes to ensure that the graphical representation of the slide creates an impact on the viewer's mind and the viewer can relate and understand the message that the presenter is trying to relay through the slide.…”