Cross-Document Event-Keyed Summarization

TL;DR

This paper introduces a new task called cross-document event-keyed summarization, extending event summarization to synthesize information from multiple sources, and provides a high-quality dataset and baseline models for it.

Contribution

The paper presents SEAMUS, a novel dataset for cross-document event summarization, and establishes baseline models and evaluations for this emerging task.

Findings

SEAMUS is a valuable benchmark for CDEKS.

Baseline models show varying performance, highlighting challenges.

Human evaluation confirms the dataset's quality.

Abstract

Event-keyed summarization (EKS) requires summarizing a specific event described in a document given the document text and an event representation extracted from it. In this work, we extend EKS to the cross-document setting (CDEKS), in which summaries must synthesize information from accounts of the same event as given by multiple sources. We introduce SEAMUS (Summaries of Events Across Multiple Sources), a high-quality dataset for CDEKS based on an expert reannotation of the FAMUS dataset for cross-document argument extraction. We present a suite of baselines on SEAMUS -- covering both smaller, fine-tuned models, as well as zero- and few-shot prompted LLMs -- along with detailed ablations and a human evaluation study, showing SEAMUS to be a valuable benchmark for this new task.