IITK at SemEval-2020 Task 10: Transformers for Emphasis Selection

TL;DR

This paper presents a transformer-based end-to-end model for emphasis selection in written text for visual media, achieving top performance in SemEval-2020 Task 10.

Contribution

The paper introduces a novel transformer-based approach for emphasis selection, demonstrating its effectiveness over previous methods.

Findings

Achieved a Matchm score of 0.810

Ranked third on the SemEval-2020 leaderboard

Transformer models outperform traditional approaches in this task

Abstract

This paper describes the system proposed for addressing the research problem posed in Task 10 of SemEval-2020: Emphasis Selection For Written Text in Visual Media. We propose an end-to-end model that takes as input the text and corresponding to each word gives the probability of the word to be emphasized. Our results show that transformer-based models are particularly effective in this task. We achieved the best Matchm score (described in section 2.2) of 0.810 and were ranked third on the leaderboard.