2020/06/09 by Tretyak, Vladislav, Stepanov, Denis
#Computation and Language (cs.CL) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2006.05354
In this research work, we present a method to generate summaries of long scientific documents that uses the advantages of both extractive and abstractive approaches. Before producing a summary in an abstractive manner, we perform the extractive step, which then is used for conditioning the abstractor module. We used pre-trained transformer-based language models, for both extractor and abstractor. Our experiments showed that using extractive and abstractive models jointly significantly improves summarization results and ROUGE scores.