Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity.
Individual user profiles and interaction histories play a significant role in providing customized experiences in real-world applications such as chatbots, social media, retail, and education.
We present a simple yet effective approach to build multilingual speech-to-text (ST) translation through efficient transfer learning from a pretrained speech encoder and text decoder.
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.
Cross-lingual document representations enable language understanding in multilingual contexts and allow transfer learning from high-resource to low-resource languages at the document level.
In this paper, we show that targeted attacks on black-box NMT systems are feasible, based on poisoning a small fraction of their parallel training data.
We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder.
As an extension of this framework, we propose a novel method to train one shared Transformer network for multilingual machine translation with different layer selection posteriors for each language pair.
Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages.
Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models.
In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task.
In this paper we describe a decision process framework allowing an agent to decide what information it should reveal to its neighbours within a communication graph in order to maximise its utility.