English

IDS at SemEval-2020 Task 10: Does Pre-trained Language Model Know What to Emphasize?

Computation and Language 2020-07-27 v1

Abstract

We propose a novel method that enables us to determine words that deserve to be emphasized from written text in visual media, relying only on the information from the self-attention distributions of pre-trained language models (PLMs). With extensive experiments and analyses, we show that 1) our zero-shot approach is superior to a reasonable baseline that adopts TF-IDF and that 2) there exist several attention heads in PLMs specialized for emphasis selection, confirming that PLMs are capable of recognizing important words in sentences.

Keywords

Cite

@article{arxiv.2007.12390,
  title  = {IDS at SemEval-2020 Task 10: Does Pre-trained Language Model Know What to Emphasize?},
  author = {Jaeyoul Shin and Taeuk Kim and Sang-goo Lee},
  journal= {arXiv preprint arXiv:2007.12390},
  year   = {2020}
}
R2 v1 2026-06-23T17:22:12.368Z