Dimsum @LaySumm 20: BART-based Approach for Scientific Document Summarization
Published in EMNLP | the First Workshop on Scholarly Document Processing, 2020
Recommended citation: Yu T, Su D, Dai W, et al. Dimsum@ LaySumm 20: BART-based Approach for Scientific Document Summarization[J]. arXiv preprint arXiv:2010.09252, 2020. https://www.aclweb.org/anthology/2020.sdp-1.35.pdf
Lay summarization aims to generate lay summaries of scientific papers automatically. It is an essential task that can increase the relevance of science for all of society. In this paper, we build a lay summary generation system based on the BART model. We leverage sentence labels as extra supervision signals to improve the performance of lay summarization. In the CL-LaySumm 2020 shared task, our model achieves 46.00% Rouge1-F1 score. Paper code slides Recommended citation: Yu T, Su D, Dai W, et al. Dimsum@ LaySumm 20: BART-based Approach for Scientific Document Summarization[J]. arXiv preprint arXiv:2010.09252, 2020.