Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation
This work addresses the challenge of enhancing translation quality for low-resource languages in machine translation, though it is incremental as it builds on an existing encoding method.
The paper tackled the problem of improving multilingual neural machine translation into low-resource languages by designing a better decoder word embedding, resulting in consistent gains of up to 1.8 BLEU on English-to-four-language translations.
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 \emph{into} the LRL, by designing a better decoder word embedding. Extending upon a general-purpose multilingual encoding method Soft Decoupled Encoding~\citep{SDE}, 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.