Statistical machine translation (SMT) treats the translation of natural language as a machine
learning problem. By examining many samples of human-produced translation, SMT …

We present a statistical machine translation model that uses hierarchical phrases—phrases
that contain subphrases. The model is formally a synchronous context-free grammar but is …

We present posterior regularization, a probabilistic framework for structured, weakly
supervised learning. Our framework efficiently incorporates indirect supervision via …

In this paper we describe a method for simplifying sentences using Phrase Based Machine
Translation, augmented with a re-ranking heuristic based on dissimilarity, and trained on a …

In tasks like semantic parsing, instruction following, and question answering, standard deep
networks fail to generalize compositionally from small datasets. Many existing approaches …

In this paper, we describe compare-mt, a tool for holistic analysis and comparison of the
results of systems for language generation tasks such as machine translation. The main goal …

Structured prediction tasks pose a fundamental trade-off between the need for model
complexity to increase predictive power and the limited computational resources for …

In adding syntax to statistical machine translation, there is a tradeoff between taking
advantage of linguistic analysis and allowing the model to exploit parallel training data with …

A major engineering challenge in statistical machine translation systems is the efficient
representation of extremely large translation rulesets. In phrase-based models, this problem …

Word reordering is one of the most difficult aspects of statistical machine translation (SMT),
and an important factor of its quality and efficiency. Despite the vast amount of research …