NEWS: News Event Walker and Summarizer

Most news summarization techniques are static, and thus do not satisfy user needs in having summaries with specific structures or details. Meanwhile, existing dynamic techniques such as query-based summarization fail to handle content-independent queries that target the type of summary information such as time, location, reasons, and consequences of reported events. The NEWS system supports multi-granular summarization along two dimensions: the level of detail and type of information. The system employs fine-grained information extraction to extract facts and their facets with type tagging. The extracted information is then modeled as a graph used to create summaries. The system incrementally expands summaries based on the nodes visited by users, folding related events into the search space.