Papers Unsupervised Machine Translation

On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation

Modern unsupervised machine translation (MT) systems reach reasonable translation quality under clean and controlled data conditions. As the performance gap between supervised and unsupervised MT narrows, it is interesti…

Unsupervised Neural Machine Translation with Universal Grammar

Machine translation usually relies on parallel corpora to provide parallel signals for training. The advent of unsupervised machine translation has brought machine translation away from this reliance, though performance …

Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language

This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German–Lower Sorbian (DE–DSB): a high-resource language to a low-res…

Multilingual Unsupervised Neural Machine Translation with Denoising Adapters

We consider the problem of multilingual unsupervised machine translation, translating to and from languages that only have monolingual data by using auxiliary parallel language pairs. For this problem the standard proced…

Leveraging Automated Unit Tests for Unsupervised Code Translation

With little to no parallel data available for programming languages, unsupervised methods are well-suited to source code translation. However, the majority of unsupervised machine translation approaches rely on back-tran…

Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots

In this paper, we explore how we can endow robots with the ability to learn correspondences between their own skills, and those of morphologically different robots in different domains, in an entirely unsupervised manner…

Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation

Modern unsupervised machine translation systems mostly train their models by generating synthetic parallel training data from large unlabeled monolingual corpora of different languages through various means, such as iter…

Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language

This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German--Lower Sorbian (DE--DSB): a high-resource language to a low-r…

Paraphrase Generation as Unsupervised Machine Translation

In this paper, we propose a new paradigm for paraphrase generation by treating the task as unsupervised machine translation (UMT) based on the assumption that there must be pairs of sentences expressing the same meaning …

Manipuri-English Machine Translation using Comparable Corpus

Unsupervised Machine Translation (MT) model, which has the ability to perform MT without parallel sentences using comparable corpora, is becoming a promising approach for developing MT in low-resource languages. However,…

Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation

Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages

For most language combinations, parallel data is either scarce or simply unavailable. To address this, unsupervised machine translation (UMT) exploits large amounts of monolingual data by using synthetic data generation …

On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation

Modern unsupervised machine translation (MT) systems reach reasonable translation quality under clean and controlled data conditions. As the performance gap between supervised and unsupervised MT narrows, it is interesti…

Break-It-Fix-It: Unsupervised Learning for Program Repair

We consider repair tasks: given a critic (e.g., compiler) that assesses the quality of an input, the goal is to train a fixer that converts a bad example (e.g., code with syntax errors) into a good one (e.g., code with n…

Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study

Recent advances in Unsupervised Neural Machine Translation (UNMT) have minimized the gap between supervised and unsupervised machine translation performance for closely related language pairs. However, the situation is v…

Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining

Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddi…

Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora

Cross-lingual text representations have gained popularity lately and act as the backbone of many tasks such as unsupervised machine translation and cross-lingual information retrieval, to name a few. However, evaluation …

Efficient Unsupervised NMT for Related Languages with Cross-Lingual Language Models and Fidelity Objectives

The most successful approach to Neural Machine Translation (NMT) when only monolingual training data is available, called unsupervised machine translation, is based on back-translation where noisy translations are genera…

Zero-Shot Language Transfer vs Iterative Back Translation for Unsupervised Machine Translation

This work focuses on comparing different solutions for machine translation on low resource language pairs, namely, with zero-shot transfer learning and unsupervised machine translation. We discuss how the data size affec…

Unsupervised Machine Translation On Dravidian Languages

Unsupervised neural machine translation (UNMT) is beneficial especially for low resource languages such as those from the Dravidian family. However, UNMT systems tend to fail in realistic scenarios involving actual low r…