Unsupervised Machine Translation
9개 벤치마크 · 논문 105편 · 이 태스크의 논문 보기 →
Benchmarks
WMT2014 English-French
WMT2014 French-English
WMT2016 English-German
WMT2016 German-English
WMT2016 English-Romanian
WMT2016 Romanian-English
WMT2014 English-German
WMT2014 German-English
Most implemented
Language Models are Few-Shot Learners
Word Translation Without Parallel Data
Cross-lingual Language Model Pretraining
Phrase-Based & Neural Unsupervised Machine Translation
Unsupervised Machine Translation Using Monolingual Corpora Only
Unsupervised Translation of Programming Languages
Papers
Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold supervision, such as ground-truth answer…
Unsupervised Machine TranslationImage-to-Image TranslationReinforcement LearningInformation RetrievalEnsemble Self-Training for Unsupervised Machine Translation
We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that share the same translation task but diff…
Unsupervised Machine TranslationPositive-Unlabelled Active Learning to Curate a Dataset for Orca Resident Interpretation
This work presents the largest curation of Southern Resident Killer Whale (SRKW) acoustic data to date, also containing other marine mammals in their environment. We systematically search all available public archival hy…
Unsupervised Machine TranslationActive LearningEffective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs
Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing (NLP) tasks, primarily through in-context learning (ICL). In ICL, the LLM is provided with examples tha…
In-Context LearningMachine TranslationTranslationUnsupervised Machine TranslationDecoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages
Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. Intuitively, with a growing number of seen languages the encoder sentence representation g…
Cross-Lingual Word EmbeddingsMachine TranslationSentenceTranslation+2The 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 Translation