July 28, 2019
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
Association for Computational Linguistics (ACL)
Given a rough, word-by-word gloss of a source language sentence, target language natives can uncover the latent, fully-fluent rendering of the translation. In this work we explore this intuition by breaking translation into a two step process: generating a rough gloss by means of a dictionary and then ‘translating’ the resulting pseudo-translation, or ‘Translationese’ into a fully fluent translation.
By: Nima Pourdamghani, Nada Aldarrab, Marjan Ghazvininejad, Kevin Knight, Jonathan May
Facebook AI Research
Natural Language Processing & Speech