@inproceedings{keles-etal-2025-cognate,
title = "Cognate and Contact-Induced Transfer Learning for Hamshentsnag: A Low-Resource and Endangered Language",
author = {Kele{\c{s}}, Onur and
G{\"u}nay, Baran and
Do{\u{g}}an, Berat},
editor = "Truong, Sang and
Putri, Rifki Afina and
Nguyen, Duc and
Wang, Angelina and
Ho, Daniel and
Oh, Alice and
Koyejo, Sanmi",
booktitle = "Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.lm4uc-1.9/",
doi = "10.18653/v1/2025.lm4uc-1.9",
pages = "76--85",
ISBN = "979-8-89176-242-8",
abstract = "This study investigates zero-shot and few-shot cross-lingual transfer effects in Part-of-Speech (POS) tagging and Named Entity Recognition (NER) for Hamshentsnag, an endangered Western Armenian dialect. We examine how different source languages, Western Armenian (contact cognate), Eastern Armenian (ancestral cognate), Turkish (substrate or contact-induced), and English (non-cognate), affect the task performance using multilingual BERT and BERTurk. Results show that cognate varieties improved POS tagging by 8{\%} F1, while the substrate source enhanced NER by 15{\%} F1. BERTurk outperformed mBERT on NER but not on POS. We attribute this to task-specific advantages of different source languages. We also used script conversion and phonetic alignment with the target for non-Latin scripts, which alleviated transfer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keles-etal-2025-cognate">
<titleInfo>
<title>Cognate and Contact-Induced Transfer Learning for Hamshentsnag: A Low-Resource and Endangered Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Keleş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baran</namePart>
<namePart type="family">Günay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berat</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sang</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rifki</namePart>
<namePart type="given">Afina</namePart>
<namePart type="family">Putri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelina</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Ho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanmi</namePart>
<namePart type="family">Koyejo</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">979-8-89176-242-8</identifier>
</relatedItem>
<abstract>This study investigates zero-shot and few-shot cross-lingual transfer effects in Part-of-Speech (POS) tagging and Named Entity Recognition (NER) for Hamshentsnag, an endangered Western Armenian dialect. We examine how different source languages, Western Armenian (contact cognate), Eastern Armenian (ancestral cognate), Turkish (substrate or contact-induced), and English (non-cognate), affect the task performance using multilingual BERT and BERTurk. Results show that cognate varieties improved POS tagging by 8% F1, while the substrate source enhanced NER by 15% F1. BERTurk outperformed mBERT on NER but not on POS. We attribute this to task-specific advantages of different source languages. We also used script conversion and phonetic alignment with the target for non-Latin scripts, which alleviated transfer.</abstract>
<identifier type="citekey">keles-etal-2025-cognate</identifier>
<identifier type="doi">10.18653/v1/2025.lm4uc-1.9</identifier>
<location>
<url>https://aclanthology.org/2025.lm4uc-1.9/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>76</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cognate and Contact-Induced Transfer Learning for Hamshentsnag: A Low-Resource and Endangered Language
%A Keleş, Onur
%A Günay, Baran
%A Doğan, Berat
%Y Truong, Sang
%Y Putri, Rifki Afina
%Y Nguyen, Duc
%Y Wang, Angelina
%Y Ho, Daniel
%Y Oh, Alice
%Y Koyejo, Sanmi
%S Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-242-8
%F keles-etal-2025-cognate
%X This study investigates zero-shot and few-shot cross-lingual transfer effects in Part-of-Speech (POS) tagging and Named Entity Recognition (NER) for Hamshentsnag, an endangered Western Armenian dialect. We examine how different source languages, Western Armenian (contact cognate), Eastern Armenian (ancestral cognate), Turkish (substrate or contact-induced), and English (non-cognate), affect the task performance using multilingual BERT and BERTurk. Results show that cognate varieties improved POS tagging by 8% F1, while the substrate source enhanced NER by 15% F1. BERTurk outperformed mBERT on NER but not on POS. We attribute this to task-specific advantages of different source languages. We also used script conversion and phonetic alignment with the target for non-Latin scripts, which alleviated transfer.
%R 10.18653/v1/2025.lm4uc-1.9
%U https://aclanthology.org/2025.lm4uc-1.9/
%U https://doi.org/10.18653/v1/2025.lm4uc-1.9
%P 76-85
Markdown (Informal)
[Cognate and Contact-Induced Transfer Learning for Hamshentsnag: A Low-Resource and Endangered Language](https://aclanthology.org/2025.lm4uc-1.9/) (Keleş et al., LM4UC 2025)
ACL