[HTML][HTML] Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
The quality of human translation was long thought to be unattainable for computer
translation systems. In this study, we present a deep-learning system, CUBBITT, which …
translation systems. In this study, we present a deep-learning system, CUBBITT, which …
Reformulating unsupervised style transfer as paraphrase generation
Modern NLP defines the task of style transfer as modifying the style of a given sentence
without appreciably changing its semantics, which implies that the outputs of style transfer …
without appreciably changing its semantics, which implies that the outputs of style transfer …
Adversarial example generation with syntactically controlled paraphrase networks
We propose syntactically controlled paraphrase networks (SCPNs) and use them to
generate adversarial examples. Given a sentence and a target syntactic form (eg, a …
generate adversarial examples. Given a sentence and a target syntactic form (eg, a …
Findings of the 2017 conference on machine translation (wmt17)
This paper presents the results of the WMT17 shared tasks, which included three machine
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …
ParaCrawl: Web-scale acquisition of parallel corpora
We report on methods to create the largest publicly available parallel corpora by crawling
the web, using open source software. We empirically compare alternative methods and …
the web, using open source software. We empirically compare alternative methods and …
Findings of the 2016 conference on machine translation (wmt16)
This paper presents the results of the WMT16 shared tasks, which included five machine
translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three …
translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three …
Training tips for the transformer model
This article describes our experiments in neural machine translation using the recent
Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et …
Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et …
ParaNMT-50M: Pushing the limits of paraphrastic sentence embeddings with millions of machine translations
We describe PARANMT-50M, a dataset of more than 50 million English-English sentential
paraphrase pairs. We generated the pairs automatically by using neural machine translation …
paraphrase pairs. We generated the pairs automatically by using neural machine translation …
Edinburgh neural machine translation systems for WMT 16
We participated in the WMT 2016 shared news translation task by building neural translation
systems for four language pairs, each trained in both directions: English<-> Czech, English< …
systems for four language pairs, each trained in both directions: English<-> Czech, English< …
Trivial transfer learning for low-resource neural machine translation
Transfer learning has been proven as an effective technique for neural machine translation
under low-resource conditions. Existing methods require a common target language …
under low-resource conditions. Existing methods require a common target language …