A related work report is a text which integrates key information from a list of related scientific papers providing context to the work being presented. In this paper we study the automatic generation of related work reports using extractive and abstractive text summarization approaches. Our extractive approach scores the sentences of the scientific papers based on their citations, selecting top scored sentences from each scientific paper to be mentioned in the related work report. The sentences ...
A related work report is a text which integrates key information from a list of related scientific papers providing context to the work being presented. In this paper we study the automatic generation of related work reports using extractive and abstractive text summarization approaches. Our extractive approach scores the sentences of the scientific papers based on their citations, selecting top scored sentences from each scientific paper to be mentioned in the related work report. The sentences are then organized in the report according to the topic they belong to. In additional experiments we use top scored sentences from our extractive methods and rephrase them using pre-trained abstractive models that generate citation sentences. We discuss automatic and manual evaluation of the generated related work reports showing the viability of the proposed approaches.
+
