@inproceedings{fane-etal-2025-bemeae,
title = "{BEMEAE}: Moving Beyond Exact Span Match for Event Argument Extraction",
author = "Fane, Enfa and
Uddin, Md Nayem and
Ikumariegbe, Oghenevovwe and
Kashif, Daniyal and
Blanco, Eduardo and
Corman, Steven",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.295/",
doi = "10.18653/v1/2025.naacl-long.295",
pages = "5734--5749",
ISBN = "979-8-89176-189-6",
abstract = "Event Argument Extraction (EAE) is a key task in natural language processing, focusing on identifying and classifying event arguments in text. However, the widely adopted exact span match (ESM) evaluation metric has notable limitations due to its rigid span constraints, often misidentifying valid predictions as errors and underestimating system performance. In this paper, we evaluate nine state-of-the-art EAE models on the RAMS and GENEVA datasets, highlighting ESM{'}s limitations. To address these issues, we introduce BEMEAE (Beyond Exact Span Match for Event Argument Extraction), a novel evaluation metric that recognizes predictions that are semantically equivalent to or improve upon the reference. BEMEAE integrates deterministic components with a semantic matching component for more accurate assessment. Our experiments demonstrate that BEMEAE aligns more closely with human judgments. We show that BEMEAE not only leads to higher F1 scores compared to ESM but also results in significant changes in model rankings, underscoring ESM{'}s inadequacy for comprehensive evaluation of EAE."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fane-etal-2025-bemeae">
<titleInfo>
<title>BEMEAE: Moving Beyond Exact Span Match for Event Argument Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enfa</namePart>
<namePart type="family">Fane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Nayem</namePart>
<namePart type="family">Uddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oghenevovwe</namePart>
<namePart type="family">Ikumariegbe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniyal</namePart>
<namePart type="family">Kashif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Blanco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Corman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Event Argument Extraction (EAE) is a key task in natural language processing, focusing on identifying and classifying event arguments in text. However, the widely adopted exact span match (ESM) evaluation metric has notable limitations due to its rigid span constraints, often misidentifying valid predictions as errors and underestimating system performance. In this paper, we evaluate nine state-of-the-art EAE models on the RAMS and GENEVA datasets, highlighting ESM’s limitations. To address these issues, we introduce BEMEAE (Beyond Exact Span Match for Event Argument Extraction), a novel evaluation metric that recognizes predictions that are semantically equivalent to or improve upon the reference. BEMEAE integrates deterministic components with a semantic matching component for more accurate assessment. Our experiments demonstrate that BEMEAE aligns more closely with human judgments. We show that BEMEAE not only leads to higher F1 scores compared to ESM but also results in significant changes in model rankings, underscoring ESM’s inadequacy for comprehensive evaluation of EAE.</abstract>
<identifier type="citekey">fane-etal-2025-bemeae</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.295</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.295/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5734</start>
<end>5749</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BEMEAE: Moving Beyond Exact Span Match for Event Argument Extraction
%A Fane, Enfa
%A Uddin, Md Nayem
%A Ikumariegbe, Oghenevovwe
%A Kashif, Daniyal
%A Blanco, Eduardo
%A Corman, Steven
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F fane-etal-2025-bemeae
%X Event Argument Extraction (EAE) is a key task in natural language processing, focusing on identifying and classifying event arguments in text. However, the widely adopted exact span match (ESM) evaluation metric has notable limitations due to its rigid span constraints, often misidentifying valid predictions as errors and underestimating system performance. In this paper, we evaluate nine state-of-the-art EAE models on the RAMS and GENEVA datasets, highlighting ESM’s limitations. To address these issues, we introduce BEMEAE (Beyond Exact Span Match for Event Argument Extraction), a novel evaluation metric that recognizes predictions that are semantically equivalent to or improve upon the reference. BEMEAE integrates deterministic components with a semantic matching component for more accurate assessment. Our experiments demonstrate that BEMEAE aligns more closely with human judgments. We show that BEMEAE not only leads to higher F1 scores compared to ESM but also results in significant changes in model rankings, underscoring ESM’s inadequacy for comprehensive evaluation of EAE.
%R 10.18653/v1/2025.naacl-long.295
%U https://aclanthology.org/2025.naacl-long.295/
%U https://doi.org/10.18653/v1/2025.naacl-long.295
%P 5734-5749
Markdown (Informal)
[BEMEAE: Moving Beyond Exact Span Match for Event Argument Extraction](https://aclanthology.org/2025.naacl-long.295/) (Fane et al., NAACL 2025)
ACL
- Enfa Fane, Md Nayem Uddin, Oghenevovwe Ikumariegbe, Daniyal Kashif, Eduardo Blanco, and Steven Corman. 2025. BEMEAE: Moving Beyond Exact Span Match for Event Argument Extraction. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5734–5749, Albuquerque, New Mexico. Association for Computational Linguistics.