Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?

Vocabulary adaptation, which integrates new vocabulary into pre-trained language models (LMs), enables expansion to new languages and mitigates token over-fragmentation. However, existing approaches are limited by their reliance on heuristic or external embeddings. We propose VocADT, a novel method...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Han, HyoJung, Eriguchi, Akiko, Xu, Haoran, Hoang, Hieu, Carpuat, Marine, Khayrallah, Huda
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!