@inproceedings{maji-bhattacharya-2025-bhashasetu,
title = "{B}hasha{S}etu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languages",
author = "Maji, Subhadip and
Bhattacharya, Arnab",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.115/",
pages = "2111--2129",
ISBN = "979-8-89176-298-5",
abstract = "Despite remarkable advances in natural language processing, developing effective systems for low-resource languages remains a formidable challenge, with performances typically lagging far behind high-resource counterparts due to data scarcity and insufficient linguistic resources. Cross-lingual knowledge transfer has emerged as a promising approach to address this challenge by leveraging resources from high-resource languages. In this paper, we investigate methods for transferring linguistic knowledge from high-resource languages to low-resource languages, where the number of labeled training instances is in hundreds. We focus on sentence-level and word-level tasks. We introduce a novel method, GETR (Graph-Enhanced Token Representation) for cross-lingual knowledge transfer along with two adopted baselines (a) augmentation in hidden layers and (b) token embedding transfer through token translation. Experimental results demonstrate that our GNN-based approach significantly outperforms existing multilingual and cross-lingual baseline methods, achieving 13 percentage point improvements on truly low-resource languages (Mizo, Khasi) for POS tagging, and 20 and 27 percentage point improvements in macro-F1 on simulated low-resource languages (Marathi, Bangla, Malayalam) across sentiment classification and NER tasks respectively. We also present a detailed analysis of the transfer mechanisms and identify key factors that contribute to successful knowledge transfer in this linguistic context."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maji-bhattacharya-2025-bhashasetu">
<titleInfo>
<title>BhashaSetu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Subhadip</namePart>
<namePart type="family">Maji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Despite remarkable advances in natural language processing, developing effective systems for low-resource languages remains a formidable challenge, with performances typically lagging far behind high-resource counterparts due to data scarcity and insufficient linguistic resources. Cross-lingual knowledge transfer has emerged as a promising approach to address this challenge by leveraging resources from high-resource languages. In this paper, we investigate methods for transferring linguistic knowledge from high-resource languages to low-resource languages, where the number of labeled training instances is in hundreds. We focus on sentence-level and word-level tasks. We introduce a novel method, GETR (Graph-Enhanced Token Representation) for cross-lingual knowledge transfer along with two adopted baselines (a) augmentation in hidden layers and (b) token embedding transfer through token translation. Experimental results demonstrate that our GNN-based approach significantly outperforms existing multilingual and cross-lingual baseline methods, achieving 13 percentage point improvements on truly low-resource languages (Mizo, Khasi) for POS tagging, and 20 and 27 percentage point improvements in macro-F1 on simulated low-resource languages (Marathi, Bangla, Malayalam) across sentiment classification and NER tasks respectively. We also present a detailed analysis of the transfer mechanisms and identify key factors that contribute to successful knowledge transfer in this linguistic context.</abstract>
<identifier type="citekey">maji-bhattacharya-2025-bhashasetu</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.115/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>2111</start>
<end>2129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BhashaSetu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languages
%A Maji, Subhadip
%A Bhattacharya, Arnab
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F maji-bhattacharya-2025-bhashasetu
%X Despite remarkable advances in natural language processing, developing effective systems for low-resource languages remains a formidable challenge, with performances typically lagging far behind high-resource counterparts due to data scarcity and insufficient linguistic resources. Cross-lingual knowledge transfer has emerged as a promising approach to address this challenge by leveraging resources from high-resource languages. In this paper, we investigate methods for transferring linguistic knowledge from high-resource languages to low-resource languages, where the number of labeled training instances is in hundreds. We focus on sentence-level and word-level tasks. We introduce a novel method, GETR (Graph-Enhanced Token Representation) for cross-lingual knowledge transfer along with two adopted baselines (a) augmentation in hidden layers and (b) token embedding transfer through token translation. Experimental results demonstrate that our GNN-based approach significantly outperforms existing multilingual and cross-lingual baseline methods, achieving 13 percentage point improvements on truly low-resource languages (Mizo, Khasi) for POS tagging, and 20 and 27 percentage point improvements in macro-F1 on simulated low-resource languages (Marathi, Bangla, Malayalam) across sentiment classification and NER tasks respectively. We also present a detailed analysis of the transfer mechanisms and identify key factors that contribute to successful knowledge transfer in this linguistic context.
%U https://aclanthology.org/2025.ijcnlp-long.115/
%P 2111-2129
Markdown (Informal)
[BhashaSetu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languages](https://aclanthology.org/2025.ijcnlp-long.115/) (Maji & Bhattacharya, IJCNLP-AACL 2025)
ACL