Machine Translation System Combination with Enhanced Alignments Using Word Embeddings

Towards a Method to Enable the Selection of Physical Models within the Systems Engineering Process: A Case Study with Simulink Models

“…These vectors represent the semantic and syntactic relationships between words, and are learned through unsupervised training on a text corpus such has Word2Vec [17]. Word embeddings can be used to improve the accuracy of tasks such as text classification [18], sentiment analysis [19], and machine translation [20]. In order to retrieve information, this approach has been presented in [21] to calculate the similarity between a query table and a set of tabular datasets, although the implemented algorithm does not consider the similarity with the input text pattern and does not apply preprocessing to the input text, as there is only one term in each cell of the table.…”

“…Models with memory Q 9 Circuits with supercapacitors Q 10 Resistors connected in parallel with diodes Q 11 Models with transfer functions Q 12 Models with switches Q 13 Models with voltages of at least 100 V Q 14 Models with a 3-phase harmonic filter Q 15 Models with SPICE resistors Q 16 Physical models with torque Q 17 Models with logical operations Q 18 A transistor connected in parallel with a resistor Q 19 Circuits with logical operations Q 20 Battery of 12 V Q 21 Models with sum operations Q 22 Bang-bang controller Q 23 AC voltage source of 100 V Q 24 Models with functions Q 25 Physical models with switches Q 26 Models with a signal input Q 27 A transistor in series with a resistor Q 28 Aerospace models Q 29 Capacitor connected with a voltage of 10 V Q 30 Models with thermocouples…”