Event-Keyed Summarization
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.
Code (1)
Tasks
Document-level Event ExtractionEvent ExtractionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cross-Document Event-Keyed Summarization
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 setti…
Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis
Feature sharing via split inference offers a lightweight alternative to federated learning for resource-constrained hospitals, but transmitted features still leak patient identity information and lack practical mechanism…
Lesion SegmentationFederated LearningLearning towards Abstractive Timeline Summarization
Timeline summarization targets at concisely summarizing the evolution trajectory along the timeline and existing timeline summarization approaches are all based on extractive methods.In this paper, we propose the task of…
Abstractive Text SummarizationDocument SummarizationTimeline SummarizationTime Series+1ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals
Retrieval shapes how language models access and ground knowledge in retrieval-augmented generation (RAG). In historical research, the target is often not an arbitrary relevant passage, but the exact record for a specific…
TWEETSUM: Event oriented Social Summarization Dataset
With social media becoming popular, a vast of short and noisy messages are produced by millions of users when a hot event happens. Developing social summarization systems becomes more and more critical for people to quic…
Extractive SummarizationRelation Network