Real-Time Web Scale Event Summarization Using Sequential Decision Making
This addresses the need for timely and comprehensive event summaries from web-scale data streams, which is incremental as it builds on prior summarization work by jointly modeling multiple criteria.
The paper tackles the problem of summarizing massive web document streams in real-time for events like the Boston marathon bombing, achieving a 28.3% improvement in summary F1 and a 43.8% improvement in time-sensitive F1 metrics.
We present a system based on sequential decision making for the online summarization of massive document streams, such as those found on the web. Given an event of interest (e.g. "Boston marathon bombing"), our system is able to filter the stream for relevance and produce a series of short text updates describing the event as it unfolds over time. Unlike previous work, our approach is able to jointly model the relevance, comprehensiveness, novelty, and timeliness required by time-sensitive queries. We demonstrate a 28.3% improvement in summary F1 and a 43.8% improvement in time-sensitive F1 metrics.