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...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Shailashree K. Sheshadri, Deepa Gupta, Biswajit Paul, J. Siva Bhavani
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2025-01-01
Saila:	IEEE Access
Gaiak:	Multilingual neural machine translation continual learning incremental language adaptation continual knowledge transfer Indic MT
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/11005970/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!