Balancing Novelty and Salience: Adaptive Learning to Rank Entities for Timeline Summarization of High-impact Events
This work addresses the need for more informative and personalized event summaries for users, though it is incremental in improving entity selection for timeline summarization.
The paper tackles the problem of timeline summarization for high-impact events by ranking entities based on a balance between salience and novelty, using an adaptive learning approach and Wikipedia-based soft labeling to capture collective attention. Experiments on a large news dataset confirm the effectiveness of the proposed methods.
Long-running, high-impact events such as the Boston Marathon bombing often develop through many stages and involve a large number of entities in their unfolding. Timeline summarization of an event by key sentences eases story digestion, but does not distinguish between what a user remembers and what she might want to re-check. In this work, we present a novel approach for timeline summarization of high-impact events, which uses entities instead of sentences for summarizing the event at each individual point in time. Such entity summaries can serve as both (1) important memory cues in a retrospective event consideration and (2) pointers for personalized event exploration. In order to automatically create such summaries, it is crucial to identify the "right" entities for inclusion. We propose to learn a ranking function for entities, with a dynamically adapted trade-off between the in-document salience of entities and the informativeness of entities across documents, i.e., the level of new information associated with an entity for a time point under consideration. Furthermore, for capturing collective attention for an entity we use an innovative soft labeling approach based on Wikipedia. Our experiments on a real large news datasets confirm the effectiveness of the proposed methods.