3 citations · 4 across the 9 of their papers we have counts for
11 papers · 1 filter
Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness
Pinzhen Chen, Koel Dutta Chowdhury, Xiaoya Xu +20
Multilingual translation benchmarks are typically sourced in English and translated into other languages, treating language pairs as the unit of evaluation---a design that is prone…
Is a Document Educational or Just Wikipedia-Style? -- Pitfalls of Classifier-Based Quality Filtering
Mateusz Klimaszewski, Piotr Andruszkiewicz
Classifier-based Quality Filtering has recently emerged as a fundamental technique in constructing pre-training corpora. The ability to deploy a single model that can replace or su…
EuroLLM-22B: Technical Report
Miguel Moura Ramos, Duarte M. Alves, Hippolyte Gisserot-Boukhlef +15
This report presents EuroLLM-22B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11…
EuroLLM-9B: Technical Report
Pedro Henrique Martins, João Alves, Patrick Fernandes +14
This report presents EuroLLM-9B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11 a…
EuroGEST: Investigating gender stereotypes in multilingual language models
Jacqueline Rowe, Mateusz Klimaszewski, Liane Guillou +2
Large language models increasingly support multiple languages, yet most benchmarks for gender bias remain English-centric. We introduce EuroGEST, a dataset designed to measure gend…
An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)
Laurie Burchell, Ona de Gibert, Nikolay Arefyev +32
Training state-of-the-art large language models requires vast amounts of clean and diverse textual data. However, building suitable multilingual datasets remains a challenge. In th…
EuroLLM: Multilingual Language Models for Europe
Pedro Henrique Martins, Patrick Fernandes, João Alves +12
The quality of open-weight LLMs has seen significant improvement, yet they remain predominantly focused on English. In this paper, we introduce the EuroLLM project, aimed at develo…
No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement
Mateusz Klimaszewski, Piotr Andruszkiewicz, Alexandra Birch
Modular deep learning is the state-of-the-art solution for lifting the curse of multilinguality, preventing the impact of negative interference and enabling cross-lingual performan…
Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation
Mateusz Klimaszewski, Piotr Andruszkiewicz, Alexandra Birch
The rise of Modular Deep Learning showcases its potential in various Natural Language Processing applications. Parameter-efficient fine-tuning (PEFT) modularity has been shown to w…
COMBO: State-of-the-Art Morphosyntactic Analysis
Mateusz Klimaszewski, Alina Wróblewska
We introduce COMBO - a fully neural NLP system for accurate part-of-speech tagging, morphological analysis, lemmatisation, and (enhanced) dependency parsing. It predicts categorica…
COMBO: a new module for EUD parsing
Mateusz Klimaszewski, Alina Wróblewska
We introduce the COMBO-based approach for EUD parsing and its implementation, which took part in the IWPT 2021 EUD shared task. The goal of this task is to parse raw texts in 17 la…