When Does Unsupervised Machine Translation Work?
Despite the reported success of unsupervised machine translation (MT), the field has yet to examine the conditions under which these methods succeed, and where they fail. We conduct an extensive empirical evaluation of unsupervised MT using dissimilar language pairs, dissimilar domains, diverse datasets, and authentic low-resource languages. We find that performance rapidly deteriorates when source and target corpora are from different domains, and that random word embedding initialization can dramatically affect downstream translation performance. We additionally find that unsupervised MT performance declines when source and target languages use different scripts, and observe very poor performance on authentic low-resource language pairs. We advocate for extensive empirical evaluation of unsupervised MT systems to highlight failure points and encourage continued research on the most promising paradigms.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationTranslationUnsupervised Machine TranslationSimilar Papers 제목 키워드 기반
The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation
Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. W…
Machine TranslationTranslationUnsupervised Machine TranslationStudy on Unsupervised Statistical Machine Translation for Backtranslation
Machine Translation systems have drastically improved over the years for several language pairs. Monolingual data is often used to generate synthetic sentences to augment the training data which has shown to improve the …
Machine TranslationTranslationUnsupervised Machine TranslationUnsupervised Pivot Translation for Distant Languages
Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German tr…
Machine TranslationNMTTranslationBilingual Lexicon Induction through Unsupervised Machine Translation
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word transla…
Bilingual Lexicon InductionLanguage ModelingLanguage ModellingMachine Translation+6Two Way Adversarial Unsupervised Word Translation
Word translation is a problem in machine translation that seeks to build models that recover word level correspondence between languages. Recent approaches to this problem have shown that word translation models can lear…
Machine TranslationTranslationVocal Bursts Valence PredictionWord Translation