Abstractive Summarization Model for Summarizing Scientific Article

Researchers consistently publish articles to contribute to science. However, it has become difficult to understand the terms employed in the document along with the way the semantic content is associated with other terms because of the rapid growth in the publication of scientific journals. Therefore, the generation of summaries based on scientific terms is more difficult with longer articles. The preparation of a summary with semantic relations between terms is addressed with graph-based techniques. However, graph-based methods are inadequately focused on generating summaries of scientific articles. To address this problem, a novel graph-based abstractive summarization (GBAS) model based on SciBERT and the graph transformer network (GTN) is proposed in this paper. The scientific content is encoded with SciBERT, terminology-related word extracts from the article with the Scientific Information Extractor (SciIE) system, and long documents are encoded and summarized with GTN. The proposed model is compared with baseline models. Experimental results show that the proposed model outperforms baseline methods in summarizing long scientific articles with ROUGE-L scores of 34.96.