After more than 70 years of evolution, great achievements have been made in machine
translation. Especially in recent years, translation quality has been greatly improved with the …

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 …

We explore six challenges for neural machine translation: domain mismatch, amount of
training data, rare words, long sentences, word alignment, and beam search. We show both …

Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by
jointly learning to align and translate. It tends to ignore past alignment information, however …

Deep learning is revolutionizing how machine translation systems are built today. This book
introduces the challenge of machine translation and evaluation-including historical …

Most recent sentence simplification systems use basic machine translation models to learn
lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods …

We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the
inclusion of pre-specified lexical constraints. The algorithm can be used with any model that …

Many language generation tasks require the production of text conditioned on both
structured and unstructured inputs. We present a novel neural network architecture which …

We present a simple log-linear reparameterization of IBM Model 2 that overcomes problems
arising from Model 1's strong assumptions and Model 2's overparameterization. Efficient …

Recent work has shown success in using neural network language models (NNLMs) as
features in MT systems. Here, we present a novel formulation for a neural network joint …