@inproceedings{you-etal-2025-event,
title = "Event-based evaluation of abstractive news summarization",
author = "You, Huiling and
Touileb, Samia and
{\O}vrelid, Lilja and
Velldal, Erik",
editor = "Arviv, Ofir and
Clinciu, Miruna and
Dhole, Kaustubh and
Dror, Rotem and
Gehrmann, Sebastian and
Habba, Eliya and
Itzhak, Itay and
Mille, Simon and
Perlitz, Yotam and
Santus, Enrico and
Sedoc, Jo{\~a}o and
Shmueli Scheuer, Michal and
Stanovsky, Gabriel and
Tafjord, Oyvind",
booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
month = jul,
year = "2025",
address = "Vienna, Austria and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.gem-1.43/",
pages = "504--510",
ISBN = "979-8-89176-261-9",
abstract = "An abstractive summary of a news article contains its most important information in a condensed version. The evaluation of automatically generated summaries by generative language models relies heavily on human-authored summaries as gold references, by calculating overlapping units or similarity scores. News articles report events, and ideally so should the summaries. In this work, we propose to evaluate the quality of abstractive summaries by calculating overlapping events between generated summaries, reference summaries, and the original news articles. We experiment on a richly annotated Norwegian dataset comprising both events annotations and summaries authored by expert human annotators. Our approach provides more insight into the event information contained in the summaries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="you-etal-2025-event">
<titleInfo>
<title>Event-based evaluation of abstractive news summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huiling</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Velldal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ofir</namePart>
<namePart type="family">Arviv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miruna</namePart>
<namePart type="family">Clinciu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Dror</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliya</namePart>
<namePart type="family">Habba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itay</namePart>
<namePart type="family">Itzhak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yotam</namePart>
<namePart type="family">Perlitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oyvind</namePart>
<namePart type="family">Tafjord</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-261-9</identifier>
</relatedItem>
<abstract>An abstractive summary of a news article contains its most important information in a condensed version. The evaluation of automatically generated summaries by generative language models relies heavily on human-authored summaries as gold references, by calculating overlapping units or similarity scores. News articles report events, and ideally so should the summaries. In this work, we propose to evaluate the quality of abstractive summaries by calculating overlapping events between generated summaries, reference summaries, and the original news articles. We experiment on a richly annotated Norwegian dataset comprising both events annotations and summaries authored by expert human annotators. Our approach provides more insight into the event information contained in the summaries.</abstract>
<identifier type="citekey">you-etal-2025-event</identifier>
<location>
<url>https://aclanthology.org/2025.gem-1.43/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>504</start>
<end>510</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Event-based evaluation of abstractive news summarization
%A You, Huiling
%A Touileb, Samia
%A Øvrelid, Lilja
%A Velldal, Erik
%Y Arviv, Ofir
%Y Clinciu, Miruna
%Y Dhole, Kaustubh
%Y Dror, Rotem
%Y Gehrmann, Sebastian
%Y Habba, Eliya
%Y Itzhak, Itay
%Y Mille, Simon
%Y Perlitz, Yotam
%Y Santus, Enrico
%Y Sedoc, João
%Y Shmueli Scheuer, Michal
%Y Stanovsky, Gabriel
%Y Tafjord, Oyvind
%S Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria and virtual meeting
%@ 979-8-89176-261-9
%F you-etal-2025-event
%X An abstractive summary of a news article contains its most important information in a condensed version. The evaluation of automatically generated summaries by generative language models relies heavily on human-authored summaries as gold references, by calculating overlapping units or similarity scores. News articles report events, and ideally so should the summaries. In this work, we propose to evaluate the quality of abstractive summaries by calculating overlapping events between generated summaries, reference summaries, and the original news articles. We experiment on a richly annotated Norwegian dataset comprising both events annotations and summaries authored by expert human annotators. Our approach provides more insight into the event information contained in the summaries.
%U https://aclanthology.org/2025.gem-1.43/
%P 504-510
Markdown (Informal)
[Event-based evaluation of abstractive news summarization](https://aclanthology.org/2025.gem-1.43/) (You et al., GEM 2025)
ACL
- Huiling You, Samia Touileb, Lilja Øvrelid, and Erik Velldal. 2025. Event-based evaluation of abstractive news summarization. In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²), pages 504–510, Vienna, Austria and virtual meeting. Association for Computational Linguistics.