A Novel Approach to Continual Knowledge Transfer in Multilingual Neural Machine Translation Using Autoregressive and Non-Autoregressive Models for Indic Languages

Recent progress in multilingual pre-trained models has significantly improved translation quality for Indic languages. However, extending these models to new languages via fine-tuning or retraining remains computationally costly and often leads to parameter interference, degrading performance on pre...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Shailashree K. Sheshadri, Deepa Gupta, Biswajit Paul, J. Siva Bhavani
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	IEEE 2025-01-01
Schriftenreihe:	IEEE Access
Schlagworte:	Multilingual neural machine translation continual learning incremental language adaptation continual knowledge transfer Indic MT
Online-Zugang:	https://ieeexplore.ieee.org/document/11005970/
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!