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 …

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 …

We propose syntactically controlled paraphrase networks (SCPNs) and use them to
generate adversarial examples. Given a sentence and a target syntactic form (eg, a …

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 …

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 …

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 …

This article describes our experiments in neural machine translation using the recent
Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et …

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 …

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< …

Transfer learning has been proven as an effective technique for neural machine translation
under low-resource conditions. Existing methods require a common target language …