Abstract: A sound attenuator for a separator device for gas and a separator device are described. The sound attenuator comprises at least one tubular member having at least one gas inlet opening in the area of one end and at least one gas outlet opening in the area of the other end. The at least one gas outlet opening is placed in the circumferential wall of the at least one tubular member near the one end and the end face at this end of the at least one tubular member is closed by a closing part.

Abstract: A method and device for processing temporal expressions from unstructured texts for filling a knowledge database. A temporal expression in a text is determined. A type of the temporal expression is determined as a function of the text. The temporal expression and the type are mapped on a prediction of a value of the temporal expression in a context-free representation of the temporal expression.

Abstract: A computer-implemented method for processing text data including a multitude of text modules. In the method, a representation of the text is provided, and a model is used which predicts a classification for a respective text module of the text as a function of the representation of the text. The provision of the representation of the text includes the provision of a total word vector for a respective text module of the text. The total word vector is formed from at least two, preferably multiple word vectors, and a respective word vector being weighted as a function of properties of the respective text module.

Abstract: A device and a computer-implemented method, for determining a similarity between data sets. A first data set that includes a plurality of first embeddings, and a second data set that includes a plurality of second embeddings, are predefined. A first model is trained on the first data set, and a second model is trained on the second data set. A set of first features of the first model is determined on the second data set, which for each second embedding includes a feature of the first model, and a set of second features of the second model is determined on the second data set, which for each second embedding includes a feature of the second model. A map that optimally maps the set of first features onto the set of second features is determined. The similarity is determined as a function of a distance of the map from a reference.

Abstract: A device and method for classifying data sets are provided. A model for solving a task, and training data sets are predefined. For each of the training data sets, a trained model for solving the task is determined by pretraining the model on the training data set and training the model on a reference training data set. A trained reference model for solving the task is determined by training the model on the reference training data set without pretraining with the plurality of training data sets. The trained models are classified as suitable or unsuitable for the pretraining as a function of a deviation of their particular quality from a reference quality. In the plurality of training data sets, nearest neighbors of a data set are determined. Each data set is classified as suitable or unsuitable for the pretraining.

Abstract: A computer-implemented method. The method includes: providing input data for a model; anonymizing at least a portion of the input data, the anonymizing including the provision of masked embeddings of the input data, and extracting pieces of information from the masked embeddings. The steps for anonymizing at least a portion of the input data and for extracting pieces of information are carried out using a hierarchical model.

Abstract: A device and method for determining a knowledge graph. A second embedding is determined for a first embedding for a word including a function. A first classification, which determines whether or not the word is an entity for the knowledge graph, or which defines to which entity or to which type of entity for the knowledge graph the word in the knowledge graph is to be assigned, is determined for the second embedding using a first classifier. A second classification, which defines to which type of embeddings from a plurality of types of embeddings the second embedding is to be assigned, is determined for the second embedding using a second classifier. At least one parameter for the function is trained in a training as a function of a gradient for the training of the first classifier and as a function of a gradient for the training of the second classifier.

Abstract: A device for the automatic analysis of multilingual text, including an embedder, which is configured for assigning a numeric representation to each of the text components from the multilingual text, and a temporal tagger, which is configured for identifying and tagging temporal expressions in the multilingual text depending on the assigned numeric representations. The embedder is configured for assigning the numeric representations of temporal expressions in such a way that it is not possible to ascertain, on the basis of the numeric representation, in which language the associated text component is written.

Abstract: A computer-implemented method for processing text data including a multitude of text modules. In the method, a representation of the text is provided, and a model is used which predicts a classification for a respective text module of the text as a function of the representation of the text. The provision of the representation of the text includes the provision of a total word vector for a respective text module of the text. The total word vector is formed from at least two, preferably multiple word vectors, and a respective word vector being weighted as a function of properties of the respective text module.

Abstract: A computer-implemented method for machine learning and processing of a digital data stream as well as devices for this purpose. A representation of a text is provided independently of a domain, a representation of a structure of the domain being provided, and a model for automatically detecting sensitive text elements being trained as a function of the representations, and data from at least a portion of the data stream, which represent a word, being replaced by data that represent a placeholder for the word, an output of the model being determined as a function of the data, data to be replaced in the data and data that replace the data to be replaced being determined as a function of the output of the model.