We present BAYESUM (for "Bayesian summarization"), a model for sentence extraction in query-focused summarization. BAYESUM leverages the common case in which multiple do...
Unlike simple questions, complex questions cannot be answered by simply extracting named entities. These questions require inferencing and synthesizing information from multiple d...
In the context of the Document Understanding Conferences, the task of Query-Focused Multi-Document Summarization is intended to improve agreement in content among humangenerated m...
The increasing complexity of summarization systems makes it difficult to analyze exactly which modules make a difference in performance. We carried out a principled comparison be...