Online learning for effort reduction in interactive neural machine translation
A Peris, F Casacuberta - Computer Speech & Language, 2019 - Elsevier
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 …
Even with this, the quality of the translations may be insufficient for some users or domains …
QuickEdit: Editing text & translations by crossing words out
D Grangier, M Auli - arXiv preprint arXiv:1711.04805, 2017 - arxiv.org
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 …
editing and to paraphrasing. Our proposal relies on very simple interactions: a human editor …
Bilingual synchronization: Restoring translational relationships with editing operations
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 …
language equivalent of some source text from scratch. We consider here a more general …
Translation technology research and human–computer interaction (HCI)
S Läubli, S Green - The Routledge handbook of translation and …, 2019 - taylorfrancis.com
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 …
measured in many ways, including automatic comparison metrics, evaluation by translators …
A reinforcement learning approach to interactive-predictive neural machine translation
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 …
reduce human effort from three directions: Firstly, instead of requiring humans to select …
Correct me if you can: Learning from error corrections and markings
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 …
cost of training data. For example, machine translation data range from costly expert …
Segment-based interactive-predictive machine translation
Abstract Machine translation systems require human revision to obtain high-quality
translations. Interactive methods provide an efficient human–computer collaboration, notably …
translations. Interactive methods provide an efficient human–computer collaboration, notably …
Interactive-predictive neural machine translation through reinforcement and imitation
We propose an interactive-predictive neural machine translation framework for easier model
personalization using reinforcement and imitation learning. During the interactive translation …
personalization using reinforcement and imitation learning. During the interactive translation …
Touch editing: A flexible one-time interaction approach for 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 …
traditional keyboard-mouse-based translation postediting. This approach relies on touch …
Learning from chunk-based feedback in neural machine translation
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 …
(NMT), when partial feedback is collected by asking users to highlight a correct chunk of a …