Cross-Document Event-Keyed Summarization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Walden, William, Kuchmiichuk, Pavlo, Martin, Alexander, Jin, Chihsheng, Cao, Angela, Sun, Claire, Allen, Curisia, White, Aaron Steven
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913613051068416
author Walden, William
Kuchmiichuk, Pavlo
Martin, Alexander
Jin, Chihsheng
Cao, Angela
Sun, Claire
Allen, Curisia
White, Aaron Steven
author_facet Walden, William
Kuchmiichuk, Pavlo
Martin, Alexander
Jin, Chihsheng
Cao, Angela
Sun, Claire
Allen, Curisia
White, Aaron Steven
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14795
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-Document Event-Keyed Summarization
Walden, William
Kuchmiichuk, Pavlo
Martin, Alexander
Jin, Chihsheng
Cao, Angela
Sun, Claire
Allen, Curisia
White, Aaron Steven
Computation and Language
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.
title Cross-Document Event-Keyed Summarization
topic Computation and Language
url https://arxiv.org/abs/2410.14795