Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
MAD-G: Multilingual Adapter Generation for Efficient Cross-Lingual Transfer
Alan Ansell (Charles University, University of Cambridge), Edoardo Maria Ponti (University of Cambridge, Mila - Quebec Artificial Intelligence Institute), Jonas Pfeiffer (Technische Universität Darmstadt), Sebastian Ruder (Google DeepMind (United Kingdom), McGill University), Goran Glavaš (University of Mannheim), Ivan Vulić (University of Cambridge), Anna Korhonen (University of Cambridge)
Résumé : Adapter modules have emerged as a general parameter-efficient means to specialize a pretrained encoder to new domains.Massively multilingual transformers (MMTs) have particularly benefited from additional training of language-specific adapters.However, this approach is not viable for the vast majority of languages, due to limitations in their corpus size or compute budgets.In this work, we propose MAD-G (Multilingual ADapter Generation), which contextually generates language adapters from language representations based on typological features.In contrast to prior work, our time-and space-efficient MAD-G approach enables (1) sharing of linguistic knowledge across languages and (2) zero-shot inference by generating language adapters for unseen languages.We thoroughly evaluate MAD-G in zero-shot crosslingual transfer on part-of-speech tagging, dependency parsing, and named entity recognition.While offering (1) improved fine-tuning efficiency (by a factor of around 50 in our experiments), (2) a smaller parameter budget, and (3) increased language coverage, MAD-G remains competitive with more expensive methods for language-specific adapter training across the board.Moreover, it offers substantial benefits for low-resource languages, particularly on the NER task in low-resource African languages.Finally, we demonstrate that MAD-G's transfer performance can be further improved via: (i) multi-source training, i.e., by generating and combining adapters of multiple languages with available taskspecific training data; and (ii) by further finetuning generated MAD-G adapters for languages with monolingual data.