Abstract: A system for generating in real-time an ad hoc actionable user interface (UI) and user experience (UX) includes one or more data sources, a visual display device for presenting actionable visual screens, and an input device for receiving external triggers. The system also includes an electronic controller programmed with UI and UX algorithms. The UI algorithm receives, from the input device, a trigger event and, from the data source(s), data contextually related to the received trigger event. The UI algorithm also determines an expected user inquiry in response to the received trigger event and contextually related data. The UI algorithm additionally generates actionable visual screen(s) having user prompt(s) corresponding to the determined expected user inquiry. The UX algorithm selects and presents on the visual display device an actionable visual screen from the generated screen(s) to generate the ad hoc actionable UI and UX.

Abstract: A system and method for machine translation are disclosed. Source sentences are received. For each source sentence, a target sentence comprising target words is generated. A plurality of translation neighbors of the target sentence is generated. Phrase alignments are computed between the source sentence and the translation neighbor. Translation neighbors are scored with a translation scoring model, based on the phrase alignment. Translation neighbors are ranked, based on the scores. In training the model, parameters of the model are updated based on an external ranking of the ranked translation neighbors. The generating of translation neighbors, scoring, ranking, and, in the case of training, updating the parameters, are iterated with one of the translation neighbors as the target sentence. In the case of decoding, one of the translation neighbors is output as a translation. The system and method may be at least partially implemented with a computer processor.

Abstract: A system and method for machine translation are disclosed. Source sentences are received. For each source sentence, a target sentence comprising target words is generated. A plurality of translation neighbors of the target sentence is generated. Phrase alignments are computed between the source sentence and the translation neighbor. Translation neighbors are scored with a translation scoring model, based on the phrase alignment. Translation neighbors are ranked, based on the scores. In training the model, parameters of the model are updated based on an external ranking of the ranked translation neighbors. The generating of translation neighbors, scoring, ranking, and, in the case of training, updating the parameters, are iterated with one of the translation neighbors as the target sentence. In the case of decoding, one of the translation neighbors is output as a translation. The system and method may be at least partially implemented with a computer processor.