SOTAVerified

Unsupervised Machine Translation

Unsupervised machine translation is the task of doing machine translation without any translation resources at training time.

( Image credit: Phrase-Based & Neural Unsupervised Machine Translation )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 102 papers

TitleStatusHype
Language Models are Few-Shot LearnersCode3
MASS: Masked Sequence to Sequence Pre-training for Language GenerationCode2
Incorporating BERT into Neural Machine TranslationCode1
Break-It-Fix-It: Unsupervised Learning for Program RepairCode1
Unsupervised Mandarin-Cantonese Machine TranslationCode1
Unsupervised Translation of Programming LanguagesCode1
Unsupervised Vision-and-Language Pre-training Without Parallel Images and CaptionsCode1
Multilingual Denoising Pre-training for Neural Machine TranslationCode1
Unsupervised Statistical Machine TranslationCode1
A Probabilistic Formulation of Unsupervised Text Style TransferCode1
On the Role of Parallel Data in Cross-lingual Transfer Learning—0
Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning—0
Comparing Unsupervised Word Translation Methods Step by Step—0
Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation—0
A Multilingual View of Unsupervised Machine Translation—0
On the Limitations of Unsupervised Bilingual Dictionary Induction—0
Orthographic Features for Bilingual Lexicon Induction—0
Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages—0
Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings—0
Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages—0
Bilingual-GAN: A Step Towards Parallel Text Generation—0
Data Selection for Unsupervised Translation of German–Upper Sorbian—0
Do all Roads Lead to Rome? Understanding the Role of Initialization in Iterative Back-Translation—0
Boosting Unsupervised Machine Translation with Pseudo-Parallel Data—0
CUNI Submission to MT4All Shared Task—0
Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs—0
Efficient Unsupervised NMT for Related Languages with Cross-Lingual Language Models and Fidelity Objectives—0
Explicit Cross-lingual Pre-training for Unsupervised Machine Translation—0
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation—0
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation—0
Off-the-Shelf Unsupervised NMT—0
Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning—0
Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages—0
Generative Models for Alignment and Data Efficiency in Language—0
Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation—0
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters—0
Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora—0
Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring—0
Generalized Data Augmentation for Low-Resource Translation—0
A Call for More Rigor in Unsupervised Cross-lingual Learning—0
Leveraging Automated Unit Tests for Unsupervised Code Translation—0
LMU Munich's Neural Machine Translation Systems at WMT 2018—0
Data-dependent Gaussian Prior Objective for Language Generation—0
Machine Translation With Weakly Paired Bilingual Documents—0
Machine Translation With Weakly Paired Documents—0
Manipuri-English Machine Translation using Comparable Corpus—0
From Unsupervised Machine Translation To Adversarial Text Generation—0
Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning—0
Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning—0
Flow-Adapter Architecture for Unsupervised Machine Translation—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.