aksw.org Research Group dataset

http://aksw.org/Projects/NeuralSPARQLMachines

Neural SPARQL Machines

Translating natural language into machine language for data access.

Abstract:
Neural SPARQL Machines translate natural language expressions into sequences encoding SPARQL queries. A generator module builds the training set from manually- or automatically-created templates and a knowledge base. The tasks of entity recognition and query construction are entirely assigned to a LSTM-based recurrent neural network. The support for external word embeddings helps tackling the vocabulary mismatch problem, while curriculum learning is employed to learn graph pattern compositions.
Project logo

Project Members

Tommaso Soru

http://aksw.org/TommasoSoru

tom@tommaso-soru.it

Diego Esteves

http://aksw.org/DiegoEsteves

esteves@informatik.uni-leipzig.de

Diego Moussallem

http://aksw.org/DiegoMoussallem

moussallem@informatik.uni-leipzig.de

Partner