Work

Fine-tune BERT for Extractive Summarization

Year: 2019
Type: preprint
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
Author: Liu, Yang
Language: English
Open Access status: green
OpenAlex ID: W2924690340
Cites: 20
Cited by: 634
Related to: 10