Group of Rochester Alumni Co-Author Paper To Be Presented At ACL 2025
Will Walden will be presenting a paper on “Cross-Document Event-Keyed Summarization” at the XLLM Workshop (https://xllms.github.io/) at ACL 2025 in Vienna, Austria (https://2025.aclweb.org/). This paper was coauthored with a group of students from Rochester and John's Hopkins University: William Walden, Pavlo Kuchmiichuk (former MS in Computational Linguistics student, current PhD in Computer Science student), Alexander Martin (former BS in Computer Science student, current PhD in Computer Science student at JHU), Chihsheng Jin (former MS in Computational Linguistics student), Angela Cao (former PhD in Lingusitics student), Claire Sun (current Brain and Cognitive Sciences PhD student), and Curisia Allen (current Computer Science and Data Science undergraduate student).
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.