Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
This addresses the problem of scaling translation systems to multiple languages efficiently, particularly for under-resourced language pairs, though it appears incremental as it builds on existing attention-based NMT methods.
The paper tackles multilingual neural machine translation by proposing a unified encoder-decoder framework that enables many-to-many translation without architectural modifications, achieving up to 2.6 BLEU point improvements in under-resourced scenarios and promising results for languages without direct parallel corpora.
In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our approach does not require any special treatment on the network architecture and it allows us to learn minimal number of free parameters in a standard way of training. Our approach has shown its effectiveness in an under-resourced translation scenario with considerable improvements up to 2.6 BLEU points. In addition, the approach has achieved interesting and promising results when applied in the translation task that there is no direct parallel corpus between source and target languages.