Over the last several years, the field of natural language processing has been propelled
forward by an explosion in the use of deep learning models. This article provides a brief …

The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

Visual understanding goes well beyond object recognition. With one glance at an image, we
can effortlessly imagine the world beyond the pixels: for instance, we can infer people's …

Optical character recognition (OCR) is one of the most popular techniques used for
converting printed documents into machine-readable ones. While OCR engines can do well …

With the development of high computational devices, deep neural networks (DNNs), in
recent years, have gained significant popularity in many Artificial Intelligence (AI) …

The field of machine translation faces an under-recognized problem because of
inconsistency in the reporting of scores from its dominant metric. Although people refer to" …

Layer normalization (LayerNorm) has been successfully applied to various deep neural
networks to help stabilize training and boost model convergence because of its capability in …

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

Character-based neural machine translation (NMT) models alleviate out-of-vocabulary
issues, learn morphology, and move us closer to completely end-to-end translation systems …

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 …