Neural machine translation systems require large amounts of training data and resources.
Even with this, the quality of the translations may be insufficient for some users or domains …

We propose a framework for computer-assisted text editing. It applies to translation post-
editing and to paraphrasing. Our proposal relies on very simple interactions: a human editor …

Machine Translation (MT) is usually viewed as a one-shot process that generates the target
language equivalent of some source text from scratch. We consider here a more general …

Understood as the relative excellence of a translation product or process, quality can be
measured in many ways, including automatic comparison metrics, evaluation by translators …

We present an approach to interactive-predictive neural machine translation that attempts to
reduce human effort from three directions: Firstly, instead of requiring humans to select …

Sequence-to-sequence learning involves a trade-off between signal strength and annotation
cost of training data. For example, machine translation data range from costly expert …

Abstract Machine translation systems require human revision to obtain high-quality
translations. Interactive methods provide an efficient human–computer collaboration, notably …

We propose an interactive-predictive neural machine translation framework for easier model
personalization using reinforcement and imitation learning. During the interactive translation …

We propose a touch-based editing method for translation, which is more flexible than
traditional keyboard-mouse-based translation postediting. This approach relies on touch …

We empirically investigate learning from partial feedback in neural machine translation
(NMT), when partial feedback is collected by asking users to highlight a correct chunk of a …