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...
Saved in:
| Main Authors: | Shailashree K. Sheshadri, Deepa Gupta, Biswajit Paul, J. Siva Bhavani |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11005970/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
The Figure of the Migrant and Multilingual Practices in Selected Lithuanian Novels and Their English Translations: Antanas Škėma’s Balta drobulė and Gabija Grušaitė’s Stasys Šaltoka / Migrandi kuju ja mitmekeelsuspraktikad valitud leedu romaanides ning...
by: Rūta Eidukevičienė, et al.
Published: (2023-12-01) -
Multilingual Autoregressive Entity Linking
by: Nicola De Cao, et al.
Published: (2022-03-01) -
TQFLL: a novel unified analytics framework for translation quality framework for large language model and human translation of allusions in multilingual corpora
by: Li Yating, et al.
Published: (2025-01-01) -
Joint Class and Domain Continual Learning for Decentralized Federated Processes
by: Chiara Lanza, et al.
Published: (2025-01-01) -
Professional Identity of the Multicultural and Multilingual Individuals in Exile
by: Tatsiana Haiden
Published: (2025-03-01)