Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation

By Nima Pourdamghani, Nada Aldarrab, Marjan Ghazvininejad, Kevin Knight, Jonathan May. 2019

25 citations recorded by the source corpus.

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. We build our Translationese decoder once from a mish-mash of parallel data that has the target language in common and then can build dictionaries on demand using unsupervised techniques, resulting in rapidly generated unsupervised neural MT systems for many source languages. We apply this process to 14 test languages, obtaining better or comparable translation results on high-resource languages than previously published unsupervised MT studies, and obtaining good quality results for low-resource languages that have never been used in an unsupervised MT scenario.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Surangika Ranathunga
  2. Ravi Shekhar
  3. Mehreen Alam
  4. E. Lee
  5. Rishemjit Kaur
  6. Marjana Prifti Skenduli

In Computer Vision and Pattern Recognition

  1. Surangika Ranathunga
  2. Ravi Shekhar
  3. Mehreen Alam
  4. E. Lee
  5. Rishemjit Kaur
  6. Marjana Prifti Skenduli

Citations in the corpus