Event-Keyed Summarization
This addresses a domain-specific problem for natural language processing researchers working with event-focused document analysis, presenting an incremental advancement by integrating existing tasks.
The paper tackles the problem of generating contextualized summaries for specific events by introducing event-keyed summarization (EKS), which combines summarization and event extraction, and shows that reducing EKS to traditional methods yields inferior results on the new MUCSUM dataset.
We introduce event-keyed summarization (EKS), a novel task that marries traditional summarization and document-level event extraction, with the goal of generating a contextualized summary for a specific event, given a document and an extracted event structure. We introduce a dataset for this task, MUCSUM, consisting of summaries of all events in the classic MUC-4 dataset, along with a set of baselines that comprises both pretrained LM standards in the summarization literature, as well as larger frontier models. We show that ablations that reduce EKS to traditional summarization or structure-to-text yield inferior summaries of target events and that MUCSUM is a robust benchmark for this task. Lastly, we conduct a human evaluation of both reference and model summaries, and provide some detailed analysis of the results.