PSED: A Dataset for Selecting Emphasis in Presentation Slides

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4314–4320 August 1–6, 2021. ©2021 Association for Computational Linguistics 4314 PSED: A Dataset for Selecting Emphasis in Presentation Slides Amirreza Shirani†, Giai Tran†, Hieu Trinh†, Franck Dernoncourt‡, Nedim Lipka‡, Jose Echevarria‡, Thamar Solorio†, and Paul Asente‡ †University of Houston ‡Adobe Research †{ashirani,gltran,httrinh,tsolorio}@uh.edu ‡{franck.dernoncourt,lipka,echevarr,asente}@adobe.com Abstract Emphasizing words in presentation slides al- lows viewers to direct their gaze to focal points without reading the entire slide, retaining their attention on the speaker. Despite many stud- ies on automatic slide generation, few have ad- dressed 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 pre- sentation slides with a wide variety of topics. We evaluated a range of state-of-the-art mod- els on this novel dataset by organizing a shared task and inviting multiple researchers to model emphasis in slides. 1 Introduction Presentation slides have become so commonplace that researchers have developed resources for de- signing effective slides (Alley and Robertshaw, 2004; Alley and Neeley, 2005; Jennings, 2009). These guidelines cover advice on the overall style, such as choosing colors and font size to ensure read- ability from a distance, as well as ways to help the content stand out more distinctly. However, recom- mendations to enhance the slides’ communication power could improve authoring even more. Our goal is predicting emphasis words in pre- sentation slides. Emphasis uses special formatting like boldface or italics to make words stand out. Well-designed emphasis can significantly increase the viewers’ retention by guiding their focus to a few words (Alley and Robertshaw, 2004). Instead of reading the entire slide, they can read only the emphasized parts, keeping their attention on the speaker and their speech, as Figure 1 illustrates.1 The Emphasis Selection (ES) task was initially introduced by Shirani et al. (2019) with a focus on 1Source: Web Marketing for Fundraisers: Get Found, Get Traffic, Get Ahead (http://www.fundraising123.o rg/files/web-marketing-for-fundraisers-g et-found-get-traffic-get-ahead652.pdf) Figure 1: The slide uses special formatting to emphasize salient content. short written text in social media, and later became a SemEval 2020 task (Shirani et al., 2020b). In this paper, we focus on presentation slides, introduc- ing a new corpus as well as automated emphasis prediction approaches. We are among the first to use the content of the slides to provide automated design assistance. Task Characteristics Emphasis selection poses new challenges specific to presentation slides. They can have different structures, and authors may fol- low traditional styles, or modern styles with more visual content. Slides cover a wide range of topics, from technical, marketing, and legal presentations to children’s illustrations. The requirement to gen- eralize to different domains and cover a variety of topics poses new challenges and encourages devel- oping robust language understanding models. We rely only on input text without additional context from the user or the rest of the design. The task is highly subjective, but the goal is straightforward: use natural language understanding techniques to discover the …

Content truncated to 500 words