papers AI Learner
The Github is limit! Click to go to the new site.

Fine-tune BERT for Extractive Summarization

2019-03-25
Yang Liu

Abstract

BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks. In this paper, we describe BERTSUM, a simple variant of BERT, for extractive summarization. Our system is the state of the art on the CNN/Dailymail dataset, outperforming the previous best-performed system by 1.65 on ROUGE-L. The codes to reproduce our results are available at https://github.com/nlpyang/BertSum

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.10318

PDF

http://arxiv.org/pdf/1903.10318


Comments

Content