Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Translation assume the existence of a pool of sentences in a source language, and rely on human annotators to provide translations or post-edits, which can still be costly. In this article, we apply active learning to a real world human-in-the-loop scenario in which we assume that: (1) the source sentences may not be readily available, but instead arrive in a stream; (2) the automatic translations receive feedback in the form of a rating, instead of a correct/edited translation, since the human-in-the-loop might be a user looking for a translation, but not be able to provide one. To tackle the challenge of deciding whether each incoming pair source–translations is worthy to query for human feedback, we resort to a number of stream-based active learning query strategies. Moreover, since we do not know in advance which query strategy will be the most adequate for a certain language pair and set of Machine Translation models, we propose to dynamically combine multiple strategies using prediction with expert advice. Our experiments on different language pairs and feedback settings show that using active learning allows to converge to the best Machine Translation systems with fewer human interactions. Furthermore, combining multiple strategies using prediction with expert advice outperforms several individual active learning strategies with even fewer interactions, particularly in partial feedback settings.

The main goal of this paper is to review and evaluate how we can take advantage of state-of-the-art machine learning techniques and apply them in wind energy operation conditions monitoring and fault diagnosis, boosting wind turbines’ availability. To accomplish this, we focus our work on analysing the current techniques in predictive maintenance, which are aimed at acting before a major failure occurs using condition monitoring. In particular, we start framing the predictive maintenance problem as an ML problem to detect patterns that indicate a fault on turbine generators. Then, we extend the problem to detect future faults. Therefore, this review will consist of analysing techniques to tackle the challenges of each machine learning stage, such as data pre-processing, feature engineering, and the selection of the best-suited model. By using specific evaluation metrics, the expected final result of using these techniques will be an improvement in the early prediction of a future fault. This improvement will have an increase in the availability of the turbine, and therefore in energy production.