Papers Unsupervised Machine Translation
“Unsupervised Machine Translation” 태그가 달린 논문 105편 · 필터 해제
From Unsupervised Machine Translation To Adversarial Text Generation
We present a self-attention based bilingual adversarial text generator (B-GAN) which can learn to generate text from the encoder representation of an unsupervised neural machine translation system. B-GAN is able to gener…
Adversarial TextDecoderMachine TranslationText Generation+2Low-Resource Unsupervised NMT: Diagnosing the Problem and Providing a Linguistically Motivated Solution
Unsupervised Machine Translation has been advancing our ability to translate without parallel data, but state-of-the-art methods assume an abundance of monolingual data. This paper investigates the scenario where monolin…
Machine TranslationNMTTranslationUnsupervised Machine Translation+1SJTU-NICT’s Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
In this paper, we introduced our joint team SJTU-NICT ‘s participation in the WMT 2020 machine translation shared task. In this shared task, we participated in four translation directions of three language pairs: English…
Collaborative FilteringLanguage ModelingLanguage ModellingMachine Translation+3UdS-DFKI@WMT20: Unsupervised MT and Very Low Resource Supervised MT for German-Upper Sorbian
This paper describes the UdS-DFKI submission to the shared task for unsupervised machine translation (MT) and very low-resource supervised MT between German (de) and Upper Sorbian (hsb) at the Fifth Conference of Machine…
Machine TranslationTranslationUnsupervised Machine TranslationData Selection for Unsupervised Translation of German–Upper Sorbian
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2020 Unsupervised Machine Translation task for German–Upper Sorbian. We investigate the usefulness of data selectio…
Machine TranslationTranslationUnsupervised Machine TranslationThe NITS-CNLP System for the Unsupervised MT Task at WMT 2020
We describe NITS-CNLP’s submission to WMT 2020 unsupervised machine translation shared task for German language (de) to Upper Sorbian (hsb) in a constrained setting i.e, using only the data provided by the organizers. We…
DecoderMachine TranslationTranslationUnsupervised Machine TranslationThe LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task
This paper describes the submission of LMU Munich to the WMT 2020 unsupervised shared task, in two language directions, German<->Upper Sorbian. Our core unsupervised neural machine translation (UNMT) system follows the s…
Machine TranslationText GenerationTranslationUnsupervised Machine TranslationUnsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such da…
Machine TranslationObject RecognitionTranslationUnsupervised Machine Translation+1Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning
Unsupervised machine translation, which utilizes unpaired monolingual corpora as training data, has achieved comparable performance against supervised machine translation. However, it still suffers from data-scarce domai…
General KnowledgeMachine TranslationMeta-LearningTransfer Learning+2SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
In this paper, we introduced our joint team SJTU-NICT 's participation in the WMT 2020 machine translation shared task. In this shared task, we participated in four translation directions of three language pairs: English…
Collaborative FilteringLanguage ModelingLanguage ModellingMachine Translation+3Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages
Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resou…
Machine TranslationTranslationUnsupervised Machine TranslationA Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation
The commonly used framework for unsupervised machine translation builds initial translation models of both translation directions, and then performs iterative back-translation to jointly boost their translation performan…
Machine TranslationNMTRetrievalSentence+2Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning
Recent neural network models have achieved impressive performance on sentiment classification in English as well as other languages. Their success heavily depends on the availability of a large amount of labeled data or …
ClassificationCross-Lingual Sentiment ClassificationDecoderGeneral Classification+8Cross-lingual Retrieval for Iterative Self-Supervised Training
Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models …
Machine TranslationRetrievalSentenceSentence Retrieval+2Unsupervised Translation of Programming Languages
A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another. Transcompilers are primarily used for interoper…
Code TranslationMachine TranslationTranslationUnsupervised Machine TranslationCross-model Back-translated Distillation for Unsupervised Machine Translation
Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently. Crucially, iterative b…
DenoisingDiversityLanguage ModelingLanguage Modelling+3Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings
Unsupervised cross-lingual word embedding (CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingual corpora. This method relies on the ass…
Cross-Lingual Word EmbeddingsData AugmentationMachine TranslationTranslation+2Language Models are Few-Shot Learners
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this me…
answerability predictionArticlesCommon Sense ReasoningCoreference Resolution+14Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting
Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak dif…
Machine TranslationTranslationUnsupervised Machine TranslationData-dependent Gaussian Prior Objective for Language Generation
For typical sequence prediction problems such as language generation, maximum likelihood estimation (MLE) has commonly been adopted as it encourages the predicted sequence most consistent with the ground-truth sequence t…
DiversityImage CaptioningL2 RegularizationMachine Translation+4