Advances 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 impressive results. Meanwhile, there are still several challenges for UNMT. This tutorial first introduces the background and the latest progress of UNMT. We then examine a number of challenges to UNMT and give empirical results on how well the technology currently holds up.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Simple and Effective Unsupervised Speech Translation
The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To…
Domain AdaptationMachine Translationspeech-recognitionSpeech Recognition+6Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination
In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source…
HallucinationMachine TranslationMultimodal Machine TranslationTranslationUnsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement
Word-level quality estimation (WQE) aims to automatically identify fine-grained error spans in machine-translated outputs and has found many uses, including assisting translators during post-editing. Modern WQE technique…
Language ModelingLanguage ModellingMachine TranslationTranslation+1Continuous Learning in Neural Machine Translation using Bilingual Dictionaries
While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machi…
LEMMAMachine TranslationOne-Shot LearningTranslationTranslating 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…
Machine TranslationTranslationUnsupervised Machine Translation