English

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

Computation and Language 2021-02-10 v2 Machine Learning

Abstract

This paper describes our proposed system for the AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides. In this specific task, given the contents of a slide we are asked to predict the degree of emphasis to be laid on each word in the slide. We propose 2 approaches to this problem including a BiLSTM-ELMo approach and a transformers based approach based on RoBERTa and XLNet architectures. We achieve a score of 0.518 on the evaluation leaderboard which ranks us 3rd and 0.543 on the post-evaluation leaderboard which ranks us 1st at the time of writing the paper.

Keywords

Cite

@article{arxiv.2101.11422,
  title  = {Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualized Embeddings},
  author = {Sreyan Ghosh and Sonal Kumar and Harsh Jalan and Hemant Yadav and Rajiv Ratn Shah},
  journal= {arXiv preprint arXiv:2101.11422},
  year   = {2021}
}

Comments

7 pages, 5 figures, 10 tables Submitted as a part of CAD-21 workshop at AAAI-2021

R2 v1 2026-06-23T22:35:09.890Z