Data augmentation has recently seen increased interest in NLP due to more work in low-
resource domains, new tasks, and the popularity of large-scale neural networks that require …

Inductive transfer learning has greatly impacted computer vision, but existing approaches in
NLP still require task-specific modifications and training from scratch. We propose Universal …

In this work we propose a simple and efficient framework for learning sentence
representations from unlabelled data. Drawing inspiration from the distributional hypothesis …

How to transfer the semantic information in a sentence to a computable numerical
embedding form is a fundamental problem in natural language processing. An informative …

Complex machine learning models for NLP are often brittle, making different predictions for
input instances that are extremely similar semantically. To automatically detect this behavior …

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 …

Sentence embedding is an important research topic in natural language processing (NLP)
since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word …

With the rapid development and popularization of Internet and mobile communication
technologies, text data mining has attracted much attention. In particular, with the wide use …

While most neural machine translation (NMT) systems are still trained using maximum
likelihood estimation, recent work has demonstrated that optimizing systems to directly …

We carry out experiments with deep learning models of summarization across the domains
of news, personal stories, meetings, and medical articles in order to understand how content …