---
title: "University of Zurich's RUMLEM Beats ML Classifiers on a Nearly Invisible Language"
subtitle: "A dictionary-driven lemmatizer covers all six Romansh varieties, hitting 80% word coverage and 95% variety identification accuracy on 30,000 texts."
url: "https://alphasignal.ai/news/university-of-zurich-s-rumlem-beats-ml-classifiers-on-a-nearly-invisible"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-13T00:00:00.000Z"
updated: "2026-08-24T02:27:03.697Z"
type: "Paper"
topics:
  - "Open Source"
  - "Data"
subtopics:
  - "Datasets"
upvotes: 963
source_url: "https://arxiv.org/abs/2604.11233"
comments: 0
truncated: true
---

# University of Zurich's RUMLEM Beats ML Classifiers on a Nearly Invisible Language

> A dictionary-driven lemmatizer covers all six Romansh varieties, hitting 80% word coverage and 95% variety identification accuracy on 30,000 texts.

Romansh is one of Switzerland's four national languages, but it barely exists in modern NLP toolchains. A team at the University of Zurich just released [RUMLEM](https://github.com/ZurichNLP/rumlem), a dictionary-based lemmatizer that finally gives the language proper morphological tooling, and as a bonus, doubles as a variety and language identifier that beats machine-learning baselines on short texts.

## A language with five siblings

Romansh is a minority Romance language spoken by roughly 40,000 to 60,000 people across several Alpine valleys of Switzerland. It comprises five regional varieties, or idioms (Sursilvan, Sutsilvan, Surmiran, Puter, and Vallader), plus Rumantsch Grischun, the supra-regional standard. The varieties diverge enough that mutual intelligibility is often limited, which is why variety-specific tooling matters.

Building one Romansh model is really building six, and until now the language has been mostly invisible to mainstream infrastructure. Romansh and its varieties are absent from popular NLP resources such as SpaCy, Universal Dependencies, and UniMorph. Prior work has tackled contextual embeddings, named entity recognition, and word alignment, but lemmatization, the task of mapping inflected word forms back to their dictionary entry, was still missing.

## Why dictionaries instead of a neural model

Neural lemmatizers usually need annotated treebanks, which do not exist for Romansh. So the authors went the other direction. Dictionary-based lemmatization is a viable alternative when a comprehensive dictionary is available, and has been used for German (via Wiktionary), Middle English, Latin, and Somali.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [RUMLEM: A Dictionary-Based Lemmatizer for Romansh](https://arxiv.org/html/2604.11233)
- [ZurichNLP/rumlem on GitHub](https://github.com/ZurichNLP/rumlem)
- [RUMLEM - Romansh Lemmatizer Demo (Hugging Face Space)](https://huggingface.co/spaces/ZurichNLP/rumlem)
- [ACL Anthology entry for RUMLEM (SwissText 2026)](https://aclanthology.org/2026.swisstext-1.11/)
- [Pledari Grond](https://pledarigrond.ch/)