Papers Unsupervised Machine Translation
“Unsupervised Machine Translation” 태그가 달린 논문 105편 · 필터 해제
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
Given a rough, word-by-word gloss of a source language sentence, target language natives can uncover the latent, fully-fluent rendering of the translation. In this work we explore this intuition by breaking translation i…
DecoderMachine TranslationSentenceTranslation+2Generalized Data Augmentation for Low-Resource Translation
Translation to or from low-resource languages LRLs poses challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing large amounts of monolingual data is regarded as an effective…
Data AugmentationMachine TranslationTranslationUnsupervised Machine TranslationMASS: Masked Sequence to Sequence Pre-training for Language Generation
Pre-training and fine-tuning, e.g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks. Inspired by the su…
Conversational Response GenerationDecoderLanguage ModelingMachine Translation+6Machine Translation With Weakly Paired Bilingual Documents
Neural machine translation, which achieves near human-level performance in some languages, strongly relies on the availability of large amounts of parallel sentences, which hinders its applicability to low-resource langu…
Machine TranslationSentenceTranslationUnsupervised Machine TranslationBilingual-GAN: A Step Towards Parallel Text Generation
Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose…
DecoderDenoisingMachine TranslationText Generation+2Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for uns…
Machine TranslationSentenceTranslationUnsupervised Machine TranslationEAT: a simple and versatile semantic representation format for multi-purpose NLP
Semantic representations are central in many NLP tasks that require human-interpretable data. The conjunctivist framework - primarily developed by Pietroski (2005, 2018) - obtains expressive representations with only a f…
Abstract Meaning RepresentationDecoderMachine TranslationStyle Transfer+2An Effective Approach to Unsupervised Machine Translation
While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems…
Machine TranslationNMTTranslationUnsupervised Machine TranslationCross-lingual Language Model Pretraining
Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingua…
Language ModelingLanguage ModellingMachine Translationmodel+3Unsupervised Neural Machine Translation with SMT as Posterior Regularization
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak super…
Machine TranslationNMTTranslationUnsupervised Machine TranslationOff-the-Shelf Unsupervised NMT
We frame unsupervised machine translation (MT) in the context of multi-task learning (MTL), combining insights from both directions. We leverage off-the-shelf neural MT architectures to train unsupervised MT models with …
Machine TranslationMulti-Task LearningNMTTranslation+1Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation
Recent work achieved remarkable results in training neural machine translation (NMT) systems in a fully unsupervised way, with new and dedicated architectures that rely on monolingual corpora only. In this work, we propo…
Machine TranslationNMTTranslationUnsupervised Machine TranslationPhrase-Based \& Neural Unsupervised Machine Translation
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to…
DenoisingMachine TranslationNMTSentence+2Phrase-based Unsupervised Machine Translation with Compositional Phrase Embeddings
This paper describes the University of Tartu{'}s submission to the unsupervised machine translation track of WMT18 news translation shared task. We build several baseline translation systems for both directions of the En…
Machine TranslationTranslationUnsupervised Machine TranslationThe LMU Munich Unsupervised Machine Translation Systems
We describe LMU Munich{'}s unsupervised machine translation systems for English↔German translation. These systems were used to participate in the WMT18 news translation shared task and more specifically, for the unsupe…
DenoisingLanguage ModelingLanguage ModellingMachine Translation+3LMU Munich's Neural Machine Translation Systems at WMT 2018
We present the LMU Munich machine translation systems for the English{--}German language pair. We have built neural machine translation systems for both translation directions (English→German and German→English) and for …
Domain AdaptationMachine TranslationTranslationUnsupervised Machine TranslationUnsupervised Statistical Machine Translation
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et a…
Language ModelingLanguage ModellingMachine TranslationNMT+2Style Transfer as Unsupervised Machine Translation
Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data…
AttributeMachine TranslationNMTSentence+3Orthographic Features for Bilingual Lexicon Induction
Recent embedding-based methods in bilingual lexicon induction show good results, but do not take advantage of orthographic features, such as edit distance, which can be helpful for pairs of related languages. This work e…
Bilingual Lexicon InductionMachine TranslationMultilingual Word EmbeddingsUnsupervised Machine Translation+2On the Limitations of Unsupervised Bilingual Dictionary Induction
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently pr…
Graph SimilarityMachine TranslationTranslationUnsupervised Machine Translation