Where did you get that? Towards Summarization Attribution for Analysts

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: B, Violet, Conroy, John M., Lynch, Sean, M, Danielle, Molino, Neil P., Wiechmann, Aaron, Yang, Julia S.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912702317723648
author B, Violet
Conroy, John M.
Lynch, Sean
M, Danielle
Molino, Neil P.
Wiechmann, Aaron
Yang, Julia S.
author_facet B, Violet
Conroy, John M.
Lynch, Sean
M, Danielle
Molino, Neil P.
Wiechmann, Aaron
Yang, Julia S.
contents Analysts require attribution, as nothing can be reported without knowing the source of the information. In this paper, we will focus on automatic methods for attribution, linking each sentence in the summary to a portion of the source text, which may be in one or more documents. We explore using a hybrid summarization, i.e., an automatic paraphrase of an extractive summary, to ease attribution. We also use a custom topology to identify the proportion of different categories of attribution-related errors.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Where did you get that? Towards Summarization Attribution for Analysts
B, Violet
Conroy, John M.
Lynch, Sean
M, Danielle
Molino, Neil P.
Wiechmann, Aaron
Yang, Julia S.
Computation and Language
Artificial Intelligence
cs.AI, cs.CL, cs.IR
Analysts require attribution, as nothing can be reported without knowing the source of the information. In this paper, we will focus on automatic methods for attribution, linking each sentence in the summary to a portion of the source text, which may be in one or more documents. We explore using a hybrid summarization, i.e., an automatic paraphrase of an extractive summary, to ease attribution. We also use a custom topology to identify the proportion of different categories of attribution-related errors.
title Where did you get that? Towards Summarization Attribution for Analysts
topic Computation and Language
Artificial Intelligence
cs.AI, cs.CL, cs.IR
url https://arxiv.org/abs/2511.08589