@inproceedings{avetisyan-broneske-2025-verbcraft,
title = "{V}erb{C}raft: Morphologically-Aware {A}rmenian Text Generation Using {LLM}s in Low-Resource Settings",
author = "Avetisyan, Hayastan and
Broneske, David",
editor = "Holdt, {\v{S}}pela Arhar and
Ilinykh, Nikolai and
Scalvini, Barbara and
Bruton, Micaella and
Debess, Iben Nyholm and
Tudor, Crina Madalina",
booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library, Estonia",
url = "https://aclanthology.org/2025.resourceful-1.25/",
pages = "111--119",
ISBN = "978-9908-53-121-2",
abstract = "Understanding and generating morphologically complex verb forms is a critical challenge in Natural Language Processing (NLP), particularly for low-resource languages like Armenian. Armenian{'}s verb morphology encodes multiple layers of grammatical information, such as tense, aspect, mood, voice, person, and number, requiring nuanced computational modeling. We introduce VerbCraft, a novel neural model that integrates explicit morphological classifiers into the mBART-50 architecture. VerbCraft achieves a BLEU score of 0.4899 on test data, compared to the baseline{'}s 0.9975, reflecting its focus on prioritizing morphological precision over fluency. With over 99{\%} accuracy in aspect and voice predictions and robust performance on rare and irregular verb forms, VerbCraft addresses data scarcity through synthetic data generation with human-in-the-loop validation. Beyond Armenian, it offers a scalable framework for morphologically rich, low-resource languages, paving the way for linguistically informed NLP systems and advancing language preservation efforts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="avetisyan-broneske-2025-verbcraft">
<titleInfo>
<title>VerbCraft: Morphologically-Aware Armenian Text Generation Using LLMs in Low-Resource Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hayastan</namePart>
<namePart type="family">Avetisyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Broneske</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="given">Arhar</namePart>
<namePart type="family">Holdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaella</namePart>
<namePart type="family">Bruton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="given">Madalina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library, Estonia</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-121-2</identifier>
</relatedItem>
<abstract>Understanding and generating morphologically complex verb forms is a critical challenge in Natural Language Processing (NLP), particularly for low-resource languages like Armenian. Armenian’s verb morphology encodes multiple layers of grammatical information, such as tense, aspect, mood, voice, person, and number, requiring nuanced computational modeling. We introduce VerbCraft, a novel neural model that integrates explicit morphological classifiers into the mBART-50 architecture. VerbCraft achieves a BLEU score of 0.4899 on test data, compared to the baseline’s 0.9975, reflecting its focus on prioritizing morphological precision over fluency. With over 99% accuracy in aspect and voice predictions and robust performance on rare and irregular verb forms, VerbCraft addresses data scarcity through synthetic data generation with human-in-the-loop validation. Beyond Armenian, it offers a scalable framework for morphologically rich, low-resource languages, paving the way for linguistically informed NLP systems and advancing language preservation efforts.</abstract>
<identifier type="citekey">avetisyan-broneske-2025-verbcraft</identifier>
<location>
<url>https://aclanthology.org/2025.resourceful-1.25/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>111</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VerbCraft: Morphologically-Aware Armenian Text Generation Using LLMs in Low-Resource Settings
%A Avetisyan, Hayastan
%A Broneske, David
%Y Holdt, Špela Arhar
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Bruton, Micaella
%Y Debess, Iben Nyholm
%Y Tudor, Crina Madalina
%S Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)
%D 2025
%8 March
%I University of Tartu Library, Estonia
%C Tallinn, Estonia
%@ 978-9908-53-121-2
%F avetisyan-broneske-2025-verbcraft
%X Understanding and generating morphologically complex verb forms is a critical challenge in Natural Language Processing (NLP), particularly for low-resource languages like Armenian. Armenian’s verb morphology encodes multiple layers of grammatical information, such as tense, aspect, mood, voice, person, and number, requiring nuanced computational modeling. We introduce VerbCraft, a novel neural model that integrates explicit morphological classifiers into the mBART-50 architecture. VerbCraft achieves a BLEU score of 0.4899 on test data, compared to the baseline’s 0.9975, reflecting its focus on prioritizing morphological precision over fluency. With over 99% accuracy in aspect and voice predictions and robust performance on rare and irregular verb forms, VerbCraft addresses data scarcity through synthetic data generation with human-in-the-loop validation. Beyond Armenian, it offers a scalable framework for morphologically rich, low-resource languages, paving the way for linguistically informed NLP systems and advancing language preservation efforts.
%U https://aclanthology.org/2025.resourceful-1.25/
%P 111-119
Markdown (Informal)
[VerbCraft: Morphologically-Aware Armenian Text Generation Using LLMs in Low-Resource Settings](https://aclanthology.org/2025.resourceful-1.25/) (Avetisyan & Broneske, RESOURCEFUL 2025)
ACL