Abstract: A device and method for determining at least one part of a knowledge graph. A body of text is made available; for one sentence from the body of text, a first, second, and third input respectively for a first, second, and third classifier is determined. Each of the first, second, and third inputs includes a numerical representation of at least one part of the sentence. A numerical representation of a first probability is determined by the first classifier as a function of the first input, which indicates whether or not the sentence relates to the knowledge graph. If the numerical representation of the first probability satisfies a first condition, a numerical representation of a second probability is determined by the second classifier as a function of the second input, which defines a first type for the word from the sentence.

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 device and method for training a model for linking a mention in textual context to an entity across knowledge bases. I the method, depending on training data, training the model for mapping an entity of a first knowledge base to its first representation in a vector space, for mapping an entity of a second knowledge base to its second representation in the vector space, for mapping the mention to a third representation in the vector space. The training data includes a set of pairs in which each pair includes a mention in a textual context and its corresponding reference entity in either the first knowledge base or the second knowledge base. Training the model includes evaluating a loss function.

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: Methods for training a relation extraction model include using dependency parsing, constituency parsing, and lexically constrained paraphrasing to augment the training data for the model. Adaptive curriculum learning is used to train the model using the augmented training data such that different scoring functions are used at different levels of training to order the training data for the curriculum learning.

Abstract: A computer-implemented method for determining an output signal characterizing a classification and/or a regression result of an input signal. The method includes: determining a feature representation characterizing the input signal; determining an intermediate signal characterizing a classification and/or regression result of the feature representation; predicting, based on the feature representation and the intermediate signal, a deviation of the intermediate signal from a desired output signal of the input signal; adapting the intermediate signal according to the determined deviation thereby determining an adapted signal; providing the adapted signal as output signal.

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 method for filling a knowledge graph. A first and second subset of data points are determined. A data point to which a label is assigned is associated with a cluster from among a set of clusters, depending on whether a distribution of labels from data points that are already associated with the cluster satisfies a condition. Data points that are associated with the cluster are associated with the first or second subset. Models for classification are trained depending on data points from the first subset. For at least one of the models, a value of a quality factor is determined depending on data points from the second subset. A model for classification is selected from the models depending on the value. A classification that defines a relationship, node, or type of node in the knowledge graph for the sentence is determined using the selected model.

Abstract: A device and method for determining at least one part of a knowledge graph. A body of text is made available; for one sentence from the body of text, a first, second, and third input respectively for a first, second, and third classifier is determined. Each of the first, second, and third inputs includes a numerical representation of at least one part of the sentence. A numerical representation of a first probability is determined by the first classifier as a function of the first input, which indicates whether or not the sentence relates to the knowledge graph. If the numerical representation of the first probability satisfies a first condition, a numerical representation of a second probability is determined by the second classifier as a function of the second input, which defines a first type for the word from the sentence.

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 and a method for determining a knowledge graph, including: providing a first entity for the knowledge graph; providing a text body; providing input data for a model that are defined as a function of the text body and the first entity of the knowledge graph; determining a prediction for a second entity and a prediction for a relationship for a triple for the knowledge graph, and a prediction for an explanation for the triple using the model as a function of the input data; determining a first probability that the model assigns to the triple and a second probability that the model assigns to the prediction for the explanation; determining a classification for the triple as a function of the first probability and of the second probability.

Abstract: A method for producing a knowledge graph having triples, in particular in the form of <entity A, entity B, relation between entity A and entity B>. The method includes: providing a body of text and input data for a model, determining with the aid of model triples including two entities of the knowledge graph and a relation between the two entities in each case, and determining an explanation for verifying the respective triple using the model. The following steps are carried out for determining a respective triple and for determining an explanation: classifying relevant areas of the body of text and discarding areas of the body of text classified as not relevant, and deriving a relation between the first entity and the second entity from the relevant areas of the body of text.

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 grouping target entities into clusters. A base association in which a cluster is associated with each of the target entities is determined in a computation step for the target entities as a function of an association for entities. Inference rules are determined as a function of the association for entities and as a function of the base association, each of the inference rules defining an association of entities with one of the clusters. An altered association is determined as a function of the association for entities and the inference rules. A check is made as to whether a difference between the base association and the altered association falls below a threshold value. When it does, an association of the target entities with the clusters is output or stored. Otherwise, a feedback value is determined as a function of the difference.

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 method for activating a machine or for machine learning or for filling a knowledge graph. Training data are made available, including texts having labels with regard to a structured piece of information. A system for classification is trained using the training data, the system for classification including an attention function that weighs individual vector representations of individual parts of a sentence as a function of weights, a classification of the sentence is determined as a function of an output of the attention function. The machine is activated in response to the input data or a knowledge graph is filled with information, i.e., expanded or built anew, in response to input data.

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.