37.2264, Software: NE-Embed: Multilingual Sentence Embedding Model for Northeast Indian Languages

The LINGUIST List linguist at listserv.linguistlist.org
Mon Jul 6 15:05:02 UTC 2026


LINGUIST List: Vol-37-2264. Mon Jul 06 2026. ISSN: 1069 - 4875.

Subject: 37.2264, Software: NE-Embed: Multilingual Sentence Embedding Model for Northeast Indian Languages

Moderator: Steven Moran (linguist at linguistlist.org)
Managing Editor: Valeriia Vyshnevetska
Team: Helen Aristar-Dry, Mara Baccaro, Daniel Swanson
Jobs: jobs at linguistlist.org | Conferences: callconf at linguistlist.org | Pubs: pubs at linguistlist.org

Homepage: http://linguistlist.org

Editor for this issue: Daniel Swanson <daniel at linguistlist.org>

================================================================


Date: 03-Jul-2026
From: Badal Nyalang [nyalang at mwirelabs.com]
Subject: NE-Embed: Multilingual Sentence Embedding Model for Northeast Indian Languages


NE-Embed is an open-source multilingual sentence embedding model
developed by MWire Labs for Northeast Indian languages. The model is
designed for semantic search, dense retrieval, retrieval-augmented
generation (RAG), multilingual information retrieval, cross-lingual
search, text similarity, clustering, duplicate detection, and
AI-powered knowledge retrieval in low-resource languages.
Built on the LaBSE architecture and fine-tuned using more than 201,000
English–Northeast Indian parallel sentence pairs, NE-Embed supports
Assamese, Bodo, Garo, Khasi, Meitei (Manipuri), Mizo, Nyishi,
Kokborok, Pnar, and Nagamese. The model is intended for researchers,
developers, digital humanities projects, government applications,
educational technology, and organizations building multilingual AI
systems for Northeast India.
NE-Embed is released under the Creative Commons Attribution 4.0
International (CC BY 4.0) license.
Model and documentation: https://huggingface.co/MWirelabs/ne-embed

Linguistic Field(s): Applied Linguistics
                     Computational Linguistics
                     Semantics

Subject Language(s): Assamese (asm, assa1263)
                     Garo (grt, garo1247)
                     Khasi (kha, khas1269)
                     Lushai (lus, lush1249)
                     Pnar (pbv, pnar1238)

Language Family(ies): Austro-Asiatic
                      Indo-Aryan (indo1321)
                      Tibeto-Burman



------------------------------------------------------------------------------

********************** LINGUIST List Support ***********************
Please consider donating to the Linguist List, a U.S. 501(c)(3) not for profit organization:

https://www.paypal.com/donate/?hosted_button_id=87C2AXTVC4PP8

LINGUIST List is supported by the following publishers:

Australian Linguistics Society https://als.asn.au/Home

Cambridge University Press http://www.cambridge.org/linguistics

Cascadilla Press http://www.cascadilla.com/

Edinburgh University Press http://www.edinburghuniversitypress.com

Language Science Press http://langsci-press.org

Lincom GmbH https://lincom-shop.eu/

Multilingual Matters http://www.multilingual-matters.com/

Wiley http://www.wiley.com


----------------------------------------------------------
LINGUIST List: Vol-37-2264
----------------------------------------------------------



More information about the LINGUIST mailing list