Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences
This addresses the challenge of machine translation for languages with limited parallel data, though it is incremental as it builds on dictionary-based and unsupervised methods.
The paper tackles the problem of machine translation without parallel sentences by using a bilingual dictionary and monolingual corpora, achieving performance comparable to supervised statistical machine translation trained on over 4 million parallel sentences on distant language pairs.
In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary. Motivated by the ability of a monolingual speaker learning to translate via looking up the bilingual dictionary, we propose the task to see how much potential an MT system can attain using the bilingual dictionary and large scale monolingual corpora, while is independent on parallel sentences. We propose anchored training (AT) to tackle the task. AT uses the bilingual dictionary to establish anchoring points for closing the gap between source language and target language. Experiments on various language pairs show that our approaches are significantly better than various baselines, including dictionary-based word-by-word translation, dictionary-supervised cross-lingual word embedding transformation, and unsupervised MT. On distant language pairs that are hard for unsupervised MT to perform well, AT performs remarkably better, achieving performances comparable to supervised SMT trained on more than 4M parallel sentences.