Background Summarization of Event Timelines
This addresses the challenge for newcomers to news events by providing historical context, though it is incremental as it builds on existing summarization methods and datasets.
The paper tackles the problem of helping newcomers catch up on news events by introducing background news summarization, which provides summaries of preceding events for each timeline update, and shows that instruction fine-tuned systems like Flan-T5 achieve strong performance, with GPT-3.5 also performing well in zero-shot settings.
Generating concise summaries of news events is a challenging natural language processing task. While journalists often curate timelines to highlight key sub-events, newcomers to a news event face challenges in catching up on its historical context. In this paper, we address this need by introducing the task of background news summarization, which complements each timeline update with a background summary of relevant preceding events. We construct a dataset by merging existing timeline datasets and asking human annotators to write a background summary for each timestep of each news event. We establish strong baseline performance using state-of-the-art summarization systems and propose a query-focused variant to generate background summaries. To evaluate background summary quality, we present a question-answering-based evaluation metric, Background Utility Score (BUS), which measures the percentage of questions about a current event timestep that a background summary answers. Our experiments show the effectiveness of instruction fine-tuned systems such as Flan-T5, in addition to strong zero-shot performance using GPT-3.5.