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.- Anthology ID:
- 2020.semeval-1.185
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Editors:
- Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 1371–1376
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.185
- DOI:
- 10.18653/v1/2020.semeval-1.185
- Cite (ACL):
- Jaeyoul Shin, Taeuk Kim, and Sang-goo Lee. 2020. IDS at SemEval-2020 Task 10: Does Pre-trained Language Model Know What to Emphasize?. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1371–1376, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- IDS at SemEval-2020 Task 10: Does Pre-trained Language Model Know What to Emphasize? (Shin et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2020.semeval-1.185.pdf