Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Phylogeny-Inspired Adaptation of Multilingual Models to New Languages

Domain:

natural language processing

Record type:

paperproject

Large pretrained multilingual models, trained on dozens of languages, have delivered promising results due to cross-lingual learning capabilities on a variety of language tasks. Further adapting these models to specific languages, especially ones unseen during pre-training, is an important goal toward expanding the coverage of language technologies. In this study, we show how we can use language phylogenetic information to improve cross-lingual transfer leveraging closely related languages in a structured, linguistically-informed manner. We perform adapter-based training on languages from diverse language families (Germanic, Uralic, Tupian, Uto-Aztecan) and evaluate on both syntactic and semantic tasks, obtaining more than 20% relative performance improvements over strong commonly used baselines, especially on languages unseen during pre-training.

Visit

aclanthology.orgarxiv.orgProject on Github

Tasks

machine translationpart of speech tagginglanguage modelingnamed entity recognitiontransfer learning

Similar

Continually Adding New Languages to Multilingual Language ModelsSmall Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource LanguagesRomanization-based Large-scale Adaptation of Multilingual Language ModelsDetecting Languages Unintelligible to Multilingual Models through Local Structure ProbesGlot500: Scaling Multilingual Corpora and Language Models to 500 LanguagesEMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models

Continually Adding New Languages to Multilingual Language Models

Multilingual language models are trained on a fixed set of languages, and to support new languages,

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages

Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due t

Romanization-based Large-scale Adaptation of Multilingual Language Models

Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for

Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes

Providing better language tools for low-resource and endangered languages is imperative for equitabl

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages

The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., makin

EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models

In this work, we introduce EMMA-500, a large-scale multilingual language model continue-trained on t