Generating Coherent Summaries of Scientific Articles Using Coherence Patterns

Previous work on automatic summarization does not thoroughly consider coherence while generating the summary. We introduce a graph-based approach to summarize scientific articles. We employ coherence patterns to ensure that the generated summaries are coherent. The novelty of our model is twofold: we mine coherence patterns in a corpus of abstracts, and we propose a method to combine coherence, importance and non-redundancy to generate the summary. We optimize these factors simultaneously using Mixed Integer Programming. Our approach significantly outperforms baseline and state-of-the-art systems in terms of coherence (summary coherence assessment) and relevance (ROUGE scores).