arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.12390cs.CL
收藏

IDS在SemEval-2020的任务10:预训练的语言模型知道要强调什么吗?

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

Seoul National University(首尔大学)

Jaeyoul Shin, Taeuk Kim, Sang-goo Lee

摘要:

我们提出了一种新的方法,使我们能够确定值得强调的文字从书面文字在视觉媒体,只依赖于信息的自我注意力分布的预训练语言模型(PLM)。通过大量的实验和分析,我们表明:1)我们的zero-shot方法是优于一个合理的基线,采用TF-IDF和2)有几个注意力头在PLM专门用于强调选择,确认PLM是能够识别句子中的重要单词。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑