Translating natural language into machine language for data access.
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.