@inproceedings{maharjan-etal-2026-benchmarking,
title = "Benchmarking Models for Low-Resource {N}epali Event Extraction with Trigger Phrase Identification and Event Classification",
author = "Maharjan, Sujal and
Shrestha, Astha and
Koduru, Lakshmojee and
Poudel, Sweta and
Shiwakoti, Shuvam and
Thapa, Rabin and
Rauniyar, Kritesh and
Thapa, Surendrabikram",
editor = {H{\"u}rriyeto{\u{g}}lu, Ali and
Thapa, Surendrabikram and
Tanev, Hristo},
booktitle = "Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications ({EEUCA} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eeuca-1.7/",
pages = "58--71",
ISBN = "979-8-89176-402-6",
abstract = "Research on Event Extraction (EE) in South Asian languages is crucial for understanding information dissemination and enabling automated news analysis in morphologically complex, low-resource environments. To address the scarcity of high-quality, publicly available datasets, we present Nepali Event Extraction (NepEE), a manually annotated corpus comprising 10,226 Devanagari sentences. The dataset includes annotations for trigger spans and event types, achieving high inter-annotator agreement with Fleiss' kappa = 0.812 for trigger identification and kappa = 0.855 for event classification. Our dataset was developed through a rigorous iterative three-phase protocol involving five expert native speakers to ensure linguistic precision. We conduct benchmarking across a broad spectrum of approaches, including classical feature-based models, five fine-tuned Transformer encoders, and contemporary instruction-tuned Large Language Models (LLMs) using zero-shot and fixed few-shot prompting. Our analysis shows that Indic-specialized Transformers achieve superior classification performance, while traditional methods and few-shot prompting struggle with the challenges of exact span extraction in morphologically complex contexts. Furthermore, we quantify performance differences between sentence-level and span-level tasks, providing strong baselines for future research. The findings and the released NepEE dataset provide a valuable resource for advancing event understanding in low-resource languages (LRLs). All code and resources are available at https://github.com/SUJAL390/EEUCA-ACL-2026-Trigger-Phrase-Identification-and-Event-Classification-in-Low-Resource-Languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maharjan-etal-2026-benchmarking">
<titleInfo>
<title>Benchmarking Models for Low-Resource Nepali Event Extraction with Trigger Phrase Identification and Event Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sujal</namePart>
<namePart type="family">Maharjan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Astha</namePart>
<namePart type="family">Shrestha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lakshmojee</namePart>
<namePart type="family">Koduru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Poudel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuvam</namePart>
<namePart type="family">Shiwakoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rabin</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kritesh</namePart>
<namePart type="family">Rauniyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hristo</namePart>
<namePart type="family">Tanev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-402-6</identifier>
</relatedItem>
<abstract>Research on Event Extraction (EE) in South Asian languages is crucial for understanding information dissemination and enabling automated news analysis in morphologically complex, low-resource environments. To address the scarcity of high-quality, publicly available datasets, we present Nepali Event Extraction (NepEE), a manually annotated corpus comprising 10,226 Devanagari sentences. The dataset includes annotations for trigger spans and event types, achieving high inter-annotator agreement with Fleiss’ kappa = 0.812 for trigger identification and kappa = 0.855 for event classification. Our dataset was developed through a rigorous iterative three-phase protocol involving five expert native speakers to ensure linguistic precision. We conduct benchmarking across a broad spectrum of approaches, including classical feature-based models, five fine-tuned Transformer encoders, and contemporary instruction-tuned Large Language Models (LLMs) using zero-shot and fixed few-shot prompting. Our analysis shows that Indic-specialized Transformers achieve superior classification performance, while traditional methods and few-shot prompting struggle with the challenges of exact span extraction in morphologically complex contexts. Furthermore, we quantify performance differences between sentence-level and span-level tasks, providing strong baselines for future research. The findings and the released NepEE dataset provide a valuable resource for advancing event understanding in low-resource languages (LRLs). All code and resources are available at https://github.com/SUJAL390/EEUCA-ACL-2026-Trigger-Phrase-Identification-and-Event-Classification-in-Low-Resource-Languages.</abstract>
<identifier type="citekey">maharjan-etal-2026-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2026.eeuca-1.7/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>58</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Models for Low-Resource Nepali Event Extraction with Trigger Phrase Identification and Event Classification
%A Maharjan, Sujal
%A Shrestha, Astha
%A Koduru, Lakshmojee
%A Poudel, Sweta
%A Shiwakoti, Shuvam
%A Thapa, Rabin
%A Rauniyar, Kritesh
%A Thapa, Surendrabikram
%Y Hürriyetoğlu, Ali
%Y Thapa, Surendrabikram
%Y Tanev, Hristo
%S Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-402-6
%F maharjan-etal-2026-benchmarking
%X Research on Event Extraction (EE) in South Asian languages is crucial for understanding information dissemination and enabling automated news analysis in morphologically complex, low-resource environments. To address the scarcity of high-quality, publicly available datasets, we present Nepali Event Extraction (NepEE), a manually annotated corpus comprising 10,226 Devanagari sentences. The dataset includes annotations for trigger spans and event types, achieving high inter-annotator agreement with Fleiss’ kappa = 0.812 for trigger identification and kappa = 0.855 for event classification. Our dataset was developed through a rigorous iterative three-phase protocol involving five expert native speakers to ensure linguistic precision. We conduct benchmarking across a broad spectrum of approaches, including classical feature-based models, five fine-tuned Transformer encoders, and contemporary instruction-tuned Large Language Models (LLMs) using zero-shot and fixed few-shot prompting. Our analysis shows that Indic-specialized Transformers achieve superior classification performance, while traditional methods and few-shot prompting struggle with the challenges of exact span extraction in morphologically complex contexts. Furthermore, we quantify performance differences between sentence-level and span-level tasks, providing strong baselines for future research. The findings and the released NepEE dataset provide a valuable resource for advancing event understanding in low-resource languages (LRLs). All code and resources are available at https://github.com/SUJAL390/EEUCA-ACL-2026-Trigger-Phrase-Identification-and-Event-Classification-in-Low-Resource-Languages.
%U https://aclanthology.org/2026.eeuca-1.7/
%P 58-71
Markdown (Informal)
[Benchmarking Models for Low-Resource Nepali Event Extraction with Trigger Phrase Identification and Event Classification](https://aclanthology.org/2026.eeuca-1.7/) (Maharjan et al., EEUCA 2026)
ACL
- Sujal Maharjan, Astha Shrestha, Lakshmojee Koduru, Sweta Poudel, Shuvam Shiwakoti, Rabin Thapa, Kritesh Rauniyar, and Surendrabikram Thapa. 2026. Benchmarking Models for Low-Resource Nepali Event Extraction with Trigger Phrase Identification and Event Classification. In Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026), pages 58–71, San Diego, California, USA. Association for Computational Linguistics.