@inproceedings{mahmoud-etal-2025-bertastic,
title = "{BERT}astic at {S}em{E}val-2025 Task 10: State-of-the-Art Accuracy in Coarse-Grained Entity Framing for {H}indi News",
author = "Mahmoud, Tarek and
Xie, Zhuohan and
Nakov, Preslav",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.55/",
pages = "386--396",
ISBN = "979-8-89176-273-2",
abstract = "We describe our system for SemEval-2025 Task 10 Subtask 1 on coarse-grained entity framing in Hindi news, exploring two complementary strategies. First, we experiment with LLM prompting using GPT-4o, comparing hierarchical multi-step prompting with native single-step prompting for both main and fine-grained role prediction. Second, we conduct an extensive study on fine-tuning XLM-R, analyzing different context granularities (full article, paragraph, or sentence-level entity mentions), monolingual vs. multilingual settings, and main vs. fine-grained role labels. Our best system, trained on fine-grained role annotations across languages using sentence-level context, achieved 43.99{\%} exact match, 56.56 {\%} precision, 47.38{\%} recall, and 51.57{\%} F1-score. Notably, our system set a new state-of-the-art for main role prediction on Hindi news, achieving 78.48 {\%} accuracy - outperforming the next best model at 76.90{\%}, as per the official leaderboard. Our findings highlight effective strategies for entity framing in multilingual and low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahmoud-etal-2025-bertastic">
<titleInfo>
<title>BERTastic at SemEval-2025 Task 10: State-of-the-Art Accuracy in Coarse-Grained Entity Framing for Hindi News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tarek</namePart>
<namePart type="family">Mahmoud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuohan</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</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 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</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">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>We describe our system for SemEval-2025 Task 10 Subtask 1 on coarse-grained entity framing in Hindi news, exploring two complementary strategies. First, we experiment with LLM prompting using GPT-4o, comparing hierarchical multi-step prompting with native single-step prompting for both main and fine-grained role prediction. Second, we conduct an extensive study on fine-tuning XLM-R, analyzing different context granularities (full article, paragraph, or sentence-level entity mentions), monolingual vs. multilingual settings, and main vs. fine-grained role labels. Our best system, trained on fine-grained role annotations across languages using sentence-level context, achieved 43.99% exact match, 56.56 % precision, 47.38% recall, and 51.57% F1-score. Notably, our system set a new state-of-the-art for main role prediction on Hindi news, achieving 78.48 % accuracy - outperforming the next best model at 76.90%, as per the official leaderboard. Our findings highlight effective strategies for entity framing in multilingual and low-resource settings.</abstract>
<identifier type="citekey">mahmoud-etal-2025-bertastic</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.55/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>386</start>
<end>396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERTastic at SemEval-2025 Task 10: State-of-the-Art Accuracy in Coarse-Grained Entity Framing for Hindi News
%A Mahmoud, Tarek
%A Xie, Zhuohan
%A Nakov, Preslav
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F mahmoud-etal-2025-bertastic
%X We describe our system for SemEval-2025 Task 10 Subtask 1 on coarse-grained entity framing in Hindi news, exploring two complementary strategies. First, we experiment with LLM prompting using GPT-4o, comparing hierarchical multi-step prompting with native single-step prompting for both main and fine-grained role prediction. Second, we conduct an extensive study on fine-tuning XLM-R, analyzing different context granularities (full article, paragraph, or sentence-level entity mentions), monolingual vs. multilingual settings, and main vs. fine-grained role labels. Our best system, trained on fine-grained role annotations across languages using sentence-level context, achieved 43.99% exact match, 56.56 % precision, 47.38% recall, and 51.57% F1-score. Notably, our system set a new state-of-the-art for main role prediction on Hindi news, achieving 78.48 % accuracy - outperforming the next best model at 76.90%, as per the official leaderboard. Our findings highlight effective strategies for entity framing in multilingual and low-resource settings.
%U https://aclanthology.org/2025.semeval-1.55/
%P 386-396
Markdown (Informal)
[BERTastic at SemEval-2025 Task 10: State-of-the-Art Accuracy in Coarse-Grained Entity Framing for Hindi News](https://aclanthology.org/2025.semeval-1.55/) (Mahmoud et al., SemEval 2025)
ACL