Learning to Emphasize: Dataset and Shared Task Models for Selecting Emphasis in Presentation Slides

TL;DR

This paper introduces a new dataset and shared task for automatic emphasis selection in presentation slides, aiming to improve design assistance by identifying key words to guide audience focus.

Contribution

It presents a novel dataset with emphasis annotations and organizes a shared task to evaluate models for emphasis selection in presentation slides.

Findings

State-of-the-art models evaluated on the dataset

Analysis of challenges in emphasis selection

Comparison of model performances

Abstract

Presentation slides have become a common addition to the teaching material. Emphasizing strong leading words in presentation slides can allow the audience to direct the eye to certain focal points instead of reading the entire slide, retaining the attention to the speaker during the presentation. Despite a large volume of studies on automatic slide generation, few studies have addressed the automation of design assistance during the creation process. Motivated by this demand, we study the problem of Emphasis Selection (ES) in presentation slides, i.e., choosing candidates for emphasis, by introducing a new dataset containing presentation slides with a wide variety of topics, each is annotated with emphasis words in a crowdsourced setting. We evaluate 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 this new domain. We present the main findings and compare the results of these models, and by examining the challenges of the dataset, we provide different analysis components.