@inproceedings{lin-zeldes-2025-gum,
title = "{GUM}-{SAGE}: A Novel Dataset and Approach for Graded Entity Salience Prediction",
author = "Lin, Jessica and
Zeldes, Amir",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.24/",
doi = "10.18653/v1/2025.findings-acl.24",
pages = "438--455",
ISBN = "979-8-89176-256-5",
abstract = "Determining and ranking the most salient entities in a text is critical for user-facing systems, especially as users increasingly rely on models to interpret long documents they only partially read. Graded entity salience addresses this need by assigning entities scores that reflect their relative importance in a text. Existing approaches fall into two main categories: subjective judgments of salience, which allow for gradient scoring but lack consistency, and summarization-based methods, which define salience as mention-worthiness in a summary, promoting explainability but limiting outputs to binary labels (entities are either summary-worthy or not). In this paper, we introduce a novel approach for graded entity salience that combines the strengths of both approaches. Using an English dataset spanning 12 spoken and written genres, we collect 5 summaries per document and calculate each entity{'}s salience score based on its presence across these summaries. Our approach shows stronger correlation with scores based on human summaries and alignments, and outperforms existing techniques, including LLMs. We release our data and code at https://github.com/jl908069/gum{\_}sum{\_}salience to support further research on graded salient entity extraction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-zeldes-2025-gum">
<titleInfo>
<title>GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</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>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Determining and ranking the most salient entities in a text is critical for user-facing systems, especially as users increasingly rely on models to interpret long documents they only partially read. Graded entity salience addresses this need by assigning entities scores that reflect their relative importance in a text. Existing approaches fall into two main categories: subjective judgments of salience, which allow for gradient scoring but lack consistency, and summarization-based methods, which define salience as mention-worthiness in a summary, promoting explainability but limiting outputs to binary labels (entities are either summary-worthy or not). In this paper, we introduce a novel approach for graded entity salience that combines the strengths of both approaches. Using an English dataset spanning 12 spoken and written genres, we collect 5 summaries per document and calculate each entity’s salience score based on its presence across these summaries. Our approach shows stronger correlation with scores based on human summaries and alignments, and outperforms existing techniques, including LLMs. We release our data and code at https://github.com/jl908069/gum_sum_salience to support further research on graded salient entity extraction.</abstract>
<identifier type="citekey">lin-zeldes-2025-gum</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.24</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.24/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>438</start>
<end>455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Prediction
%A Lin, Jessica
%A Zeldes, Amir
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F lin-zeldes-2025-gum
%X Determining and ranking the most salient entities in a text is critical for user-facing systems, especially as users increasingly rely on models to interpret long documents they only partially read. Graded entity salience addresses this need by assigning entities scores that reflect their relative importance in a text. Existing approaches fall into two main categories: subjective judgments of salience, which allow for gradient scoring but lack consistency, and summarization-based methods, which define salience as mention-worthiness in a summary, promoting explainability but limiting outputs to binary labels (entities are either summary-worthy or not). In this paper, we introduce a novel approach for graded entity salience that combines the strengths of both approaches. Using an English dataset spanning 12 spoken and written genres, we collect 5 summaries per document and calculate each entity’s salience score based on its presence across these summaries. Our approach shows stronger correlation with scores based on human summaries and alignments, and outperforms existing techniques, including LLMs. We release our data and code at https://github.com/jl908069/gum_sum_salience to support further research on graded salient entity extraction.
%R 10.18653/v1/2025.findings-acl.24
%U https://aclanthology.org/2025.findings-acl.24/
%U https://doi.org/10.18653/v1/2025.findings-acl.24
%P 438-455
Markdown (Informal)
[GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Prediction](https://aclanthology.org/2025.findings-acl.24/) (Lin & Zeldes, Findings 2025)
ACL