An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contribution
Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised methods and analyzing its output in aspects other than translation accuracy. We focus on three very diverse languages, French, Gujarati, and Kazakh, and train bilingual NMT models, to and from English, with various levels of supervision, in high- and low- resource setups, measure quality of the NMT output and compare the generated sequences' word order and semantic similarity to source and reference sentences. We also use Layer-wise Relevance Propagation to evaluate the source and target sentences' contribution to the result, expanding the findings of previous works to the UNMT paradigm.
Code (0)
등록된 구현이 없습니다.
Tasks
Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationNMTSemantic SimilaritySemantic Textual SimilarityTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Multilingual View of Unsupervised Machine Translation
We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. In addition to studying the vanilla case where t…
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 TranslationCross-lingual Supervision Improves Unsupervised Neural Machine Translation
Neural machine translation~(NMT) is ineffective for zero-resource languages. Recent works exploring the possibility of unsupervised neural machine translation (UNMT) with only monolingual data can achieve promising resul…
Machine TranslationNMTTranslationUnsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation
Unsupervised bilingual word embedding (UBWE), together with other technologies such as back-translation and denoising, has helped unsupervised neural machine translation (UNMT) achieve remarkable results in several langu…
DecoderDenoisingMachine TranslationTranslationAdvances and Challenges in Unsupervised Neural Machine Translation
Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved…
DenoisingMachine TranslationTranslation