# Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation

arXiv: https://arxiv.org/abs/2010.01667 · HTML: https://mlsanity.com/paper/2010.01667/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages](https://mlsanity.com/paper/2203.01976/) (2022)
- [Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study](https://mlsanity.com/paper/2106.03958/) (2021)
- [CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.00665/) (2022)
- [Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?](https://mlsanity.com/paper/2503.24102/) (2025)
- [Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation](https://mlsanity.com/paper/2402.01772/) (2024)

## Abstract (arXiv)

To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL). However, multilingual data has been found more beneficial for NMT models that translate from the LRL to a target language than the ones that translate into the LRLs. In this paper, we aim to improve the effectiveness of multilingual transfer for NMT models that translate into the LRL, by designing a better decoder word embedding. Extending upon a general-purpose multilingual encoding method Soft Decoupled Encoding~citepSDE, we propose DecSDE, an efficient character n-gram based embedding specifically designed for the NMT decoder. Our experiments show that DecSDE leads to consistent gains of up to 1.8 BLEU on translation from English to four different languages.