We propose a summarization approach for scientific articles which takesadvantage of citation-context and the document discourse model. While citationshave been previously used in generating scientific summaries, they lack therelated context from the referenced article and therefore do not accuratelyreflect the article's content. Our method overcomes the problem ofinconsistency between the citation summary and the article's content byproviding context for each citation. We also leverage the inherent scientificarticle's discourse for producing better summaries. We show that our proposedmethod effectively improves over existing summarization approaches (greaterthan 30% improvement over the best performing baseline) in terms of\textsc{Rouge} scores on TAC2014 scientific summarization dataset. While thedataset we use for evaluation is in the biomedical domain, most of ourapproaches are general and therefore adaptable to other domains.
展开▼