Robert Boschgmbh

Jannik Stroetgen

Lukas Lange

Heike Adel-Vu

Simon Razniewski

Anastasiia Iurshina

Ioannis Dikeoulias

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.

Device and in particular a computer-implemented method for classifying data sets

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.

Device and method for determining a knowledge graph

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.

Device for an automated generation of a knowledge graph

A method for predicting a persistence over time of entries of a knowledge base variable over time, the knowledge base including triples of entities, property identifiers of properties of the respective entities, and expressions of these respective properties, the prediction being made as a function of an output value of a classifier, and the classifier being trained as a function of triples that are present in the knowledge base at two different points in time separated by a time interval, to output the output value that characterizes for a predefinable triple whether or not the expression stored in the triple is stable over this time interval.

Method for predicting a persistence over time of entries of a knowledge base

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.

Growing community of inventors

Karlsruhe, Germany

Jannik Stroetgen