International Journal of Technology and Applied Science

E-ISSN: 2230-9004   •   Impact Factor: 9.914

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 17 Issue 5 (May 2026) Submit your research before the last 3 days of this month to publish your research paper in the current issue.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 17 Issue 5
May 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Multilingual NLP Systems for Low-resource Languages

Author(s) Mrs. K. Swapna, P. Riya, B. Hari Priya, D. Sangeetha, N. Sowmya
Country India
Abstract India is home to many different languages, but some are not getting much attention. These languages have few digital records, not many tagged texts, and not much help from technology. Working on natural language processing (NLP) in India is tough because of the many different ways people speak, the complex rules of each language, and the lack of standard benchmarks. To deal with this, systems are being developed that are not one-size-fits-all but are tailored to fit the needs of these overlooked languages. These systems quietly help close the gap without making a big deal about it. One way to handle this is by learning from languages that have a lot of data, such as Hindi, English, or Tamil, and then applying that knowledge to languages with less data. Instead of starting from scratch for each language, models can borrow knowledge from one language to improve another. Techniques like transfer learning, word maps that span multiple languages, and network designs built for handling different contexts are being tested when there's not a lot of data available. Multilingual models perform much better than single-language models when it comes to languages with limited data [3] Transfer learning and cross-lingual embeddings let models share knowledge across languages. Semi-supervised and unsupervised methods help use limited labeled data more effectively. These approaches greatly improve NLP performance for low-resource Indian languages and support digital inclusion. With no need for endless labeled examples, the hidden structures in raw text start to show up thanks to unguided training styles. Even partial labels can help nudge the system forward under half-guided setups. What’s special here is how it brings together traits that are common in Indian languages, like word structure and different scripts, because these are often found in everyday conversations. These models are tested across various language tasks, such as translating speech from one language to another, detecting emotions in text, and extracting names from sentences. All these tasks are aimed at checking how well the models adapt while maintaining strong performance. It turns out multilingual models work much better than single-language models for languages with little data. [4] What stands out is how working together on datasets, sharing tools freely, and involving local communities can make a real difference for less common languages in natural language processing.
Field Engineering
Published In Volume 17, Issue 4, April 2026
Published On 2026-04-12
Cite This Multilingual NLP Systems for Low-resource Languages - Mrs. K. Swapna, P. Riya, B. Hari Priya, D. Sangeetha, N. Sowmya - IJTAS Volume 17, Issue 4, April 2026. DOI 10.71097/IJTAS.v17.i4.1258
DOI https://doi.org/10.71097/IJTAS.v17.i4.1258
Short DOI https://doi.org/hbxc4s
View / Download PDF File

Share this



CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJTAS DOI prefix is
10.71097/IJTAS

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 12Cover Page Vol 15 Isu 11Cover Page Vol 15 Isu 10

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJTAS
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us Message on WhatsApp +91-9687-182-185 editor@ijtas.com