Renaissance Labs

Atlas / Europe

Academic lab · Munich, Germany

CIS, LMU Munich

LMU Munich's language processing centre, behind SimAlign, Glot500 and GlotLID for massively multilingual NLP.

multilingual NLPlow-resource languageslanguage identification

Munich, Germany

Founded
2017
Type
Academic lab
Based in
Munich, Germany
Key papers
3
Featured projects
8

About

The Center for Information and Language Processing at LMU Munich hosts a deep NLP group led by Hinrich Schütze, whose GitHub organization dates from 2017. Its work targets low-resource and multilingual language technology.

SimAlign (2020) is a word alignment tool, Glot500 (2023) scales corpora and models to 500 languages, and GlotLID is a language identification model that covered 1665 languages in its first version and over 2,000 labels in v3.0 as of April 2024.

Authors include Amir Hossein Kargaran, Ayyoob Imani and Schütze, and the data and models are published on GitHub and Hugging Face.

Mission and ambitions

The group aims to extend language technology to many more of the world's languages and to publish the resulting data and models openly.

Known for

  1. 01

    GlotLID language identification

  2. 02

    Glot500 multilingual corpus and model

  3. 03

    SimAlign word alignment

  4. 04

    Low-resource language support

Milestones

  1. 2020

    SimAlign

    Released a word alignment tool (arXiv 2004.08728).

  2. 2023

    Glot500

    Scaled corpora and language models to 500 languages (arXiv 2305.12182).

  3. 2023

    GlotLID

    Released a language identification model for low-resource languages (arXiv 2310.16248).

  4. 2024

    GlotLID v3.0

    Updated the model to more than 2,000 labels.

Open source

GitHubgithub.com/cisnlp
  • [EMNLP 2020] Obtain Word Alignments using Pretrained Language Models (e.g., mBERT) (397 stars)

  • [EMNLP 2023] 💬 Language Identification with Support for More Than 2000 Labels (228 stars)

  • [ACL 2023] Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages (109 stars)

  • [LREC 2024] 🖋 Resource and Tool for Writing System Identification (25 stars)

Hugging Facehuggingface.co/cis-lmu

Research papers

Notable releases

Openness

Code, models and corpora are public on GitHub and Hugging Face.

People

Listed from the lab's own pages and public profiles.

Contact and community

Contact through the group website.

Sources

Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.

Labs nearby